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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    structured data formats, specifically JSON schema.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     swe
    -0.07
    (first
    -0.06
    )[-
    -0.06
    疗
    -0.06
    decimal
    -0.06
    sou
    -0.06
     Devon
    -0.06
     Sau
    -0.06
    ([])↵
    -0.06
     exercises
    -0.06
    POSITIVE LOGITS
     enclosure
    0.06
     oltre
    0.06
    EK
    0.06
     Nr
    0.06
     getEmail
    0.06
    _arch
    0.05
     considering
    0.05
     Ή
    0.05
    _d
    0.05
    олит
    0.05
    Act Density 0.018%

    No Known Activations