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

    Neuronpedia

    INDEX
    Explanations

    words related to computer code/programming, particularly related to validation and conversion.

    oai_token-act-pair · gemini-2.0-flash

    programming terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.83
     doInBackground
    -0.80
     Мексичка
    -0.79
    ագրություններ
    -0.78
    findpost
    -0.77
     للاسماء
    -0.73
     NSCoder
    -0.72
     onCreateView
    -0.69
     Савезне
    -0.69
    rungsseite
    -0.68
    POSITIVE LOGITS
     poč
    0.49
     reason
    0.47
    ksa
    0.47
    engel
    0.46
    reason
    0.46
    bited
    0.43
    பு
    0.41
    ButterKnife
    0.41
    al
    0.40
    ده
    0.39
    Act Density 2.729%

    No Known Activations