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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash

    This neuron fires on the opening word of a quoted utterance—especially sentence-initial pronouns or imperatives like “She,” “Don’t,” “You,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Loan
    -0.07
     maint
    -0.06
     Deposit
    -0.06
     stehen
    -0.06
     Seven
    -0.06
    _intro
    -0.06
     Searches
    -0.06
    طع
    -0.06
    疗
    -0.06
     Professional
    -0.06
    POSITIVE LOGITS
            
↵        
↵
    0.07
    avicon
    0.06
    pill
    0.06
     PHYS
    0.06
     ιστο
    0.06
    โดย
    0.06
    etal
    0.06
    .compile
    0.06
    -about
    0.06
    ;">
↵
    0.06
    Act Density 0.099%

    No Known Activations