Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    writing and editing

    np_max-act · gemini-2.0-flash

    steps and advice related to the process of writing a book.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on instructional, process‐oriented language—terms describing steps, stages, or procedural aspects (e.g. “process,” “draft,” “revise,” “complex,” “lengthy”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cmd
    -0.07
     тра
    -0.07
    　　　　
    -0.06
    -0.06
     file
    -0.06
     aproxim
    -0.06
    checksum
    -0.06
    StartDate
    -0.06
     punish
    -0.06
    agency
    -0.06
    POSITIVE LOGITS
     arist
    0.06
    -toast
    0.06
    VERS
    0.06
     Mack
    0.06
     Bound
    0.06
    IDL
    0.06
     zeměděl
    0.06
     userRepository
    0.06
    [(
    0.06
    dbname
    0.06
    Act Density 0.028%

    No Known Activations