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

    Neuronpedia

    INDEX
    Explanations

    key actions or conclusions in legal or formal documents

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

    follow "click here"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.89
    GraphicsUnit
    -0.88
     defaultstate
    -0.80
     invokingState
    -0.78
     ब्रेकडाउन
    -0.77
    parsedMessage
    -0.73
    UserScript
    -0.72
     kasarigan
    -0.71
    AutoField
    -0.70
     ſche
    -0.69
    POSITIVE LOGITS
     
    0.39
    ,
    0.36
     OF
    0.35
    ato
    0.34
    ↵↵↵
    0.34
     I
    0.34
    </tr>
    0.34
    ↵
    0.34
     them
    0.32
     ,
    0.32
    Act Density 0.129%

    No Known Activations