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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or acknowledgment in conversations

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

    affirmative responses and exclamations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.62
    تقاوى
    -0.49
    原始内容存档于
    -0.46
    Nuorodos
    -0.44
     الرياضيه
    -0.44
    |};
    -0.44
    Dtor
    -0.43
    ?>">
    -0.40
     оригіналу
    -0.40
    ombies
    -0.40
    POSITIVE LOGITS
    parsedMessage
    0.56
     GenerationType
    0.46
    InjectAttribute
    0.46
    CloseOperation
    0.45
     Numerade
    0.42
    moveToFirst
    0.40
    PYX
    0.38
    AccessorTable
    0.38
     👆
    0.38
     Confe
    0.38
    Act Density 0.087%

    No Known Activations