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

    Neuronpedia

    INDEX
    Explanations

    Knock knock jokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ladı
    0.93
     ntawm
    0.77
     threes
    0.76
    燴
    0.76
     matières
    0.75
    ల
    0.75
    ниц
    0.73
    giveness
    0.73
    ಶಿ
    0.72
    ları
    0.71
    POSITIVE LOGITS
    ς
    0.75
    с
    0.74
     copol
    0.70
     زمن
    0.69
    concent
    0.69
     PowerShell
    0.69
     TR
    0.68
    notation
    0.68
    assumption
    0.68
     Symfony
    0.67
    Act Density 0.001%

    No Known Activations