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

    Neuronpedia

    INDEX
    Explanations

    dialogue punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.80
    :
    0.75
    ,
    0.71
     economic
    0.69
     its
    0.68
     values
    0.68
     any
    0.67
     elements
    0.67
     maximum
    0.67
     derivatives
    0.66
    POSITIVE LOGITS
     exclaimed
    0.75
    揶
    0.74
     جواب
    0.72
     Honestly
    0.71
    Honestly
    0.71
     আমি
    0.70
    reply
    0.70
    Smiling
    0.70
     divertida
    0.70
     Antwort
    0.68
    Act Density 0.033%

    No Known Activations