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

    Neuronpedia

    INDEX
    Explanations

    references to models, methods, and classifications within technical contexts

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

    preceding "algorithm", "model", "option", or "assumption"

    np_acts-logits-general · gemini-2.0-flash

    technical computation concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.88
     Normdatei
    -0.86
     للاسماء
    -0.81
     beginnetje
    -0.79
    ftagPool
    -0.77
     Administrativna
    -0.74
    PYX
    -0.73
     utafitiHapana
    -0.72
    yntaxException
    -0.68
    Enllaces
    -0.67
    POSITIVE LOGITS
    XmlAccessType
    0.74
     (
    0.63
    ⓧ
    0.54
     ​​
    0.53
     mad
    0.50
    WebpackPlugin
    0.48
    页面存档备份
    0.48
     [
    0.47
    ↵↵↵
    0.46
    providedIn
    0.45
    Act Density 1.915%

    No Known Activations