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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structure in code

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

    Tokens preceding HTML-like attributes

    np_acts-logits-general · gemini-2.0-flash

    degrading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alnız
    -0.54
     standard
    -0.53
    //
    -0.52
    oté
    -0.52
    ocan
    -0.51
     purpoſe
    -0.51
     special
    -0.50
     ISNI
    -0.49
    ellus
    -0.49
     ſmall
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.73
    出版年
    0.61
     الحره
    0.61
     assurent
    0.60
    κτηρισ
    0.58
    SourceChecksum
    0.58
    ftagPool
    0.54
    UrlResolution
    0.54
     BitmapFactory
    0.52
     aihe
    0.50
    Act Density 0.200%

    No Known Activations