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

    Neuronpedia

    INDEX
    Explanations

    references to qualified professionals and specialists in various fields

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

    legal and technical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     volume
    -0.32
     
    -0.30
     shock
    -0.28
     giriş
    -0.28
     aufge
    -0.28
    Volume
    -0.28
    াপ
    -0.28
    String
    -0.28
    ↵↵
    -0.27
    物
    -0.27
    POSITIVE LOGITS
    InjectAttribute
    0.84
    Autoritní
    0.82
    adpleegd
    0.72
    SharedDtor
    0.72
     myſelf
    0.68
    Personensuche
    0.66
     GenerationType
    0.66
    drawSprites
    0.66
    ſelben
    0.66
    majánló
    0.65
    Act Density 0.027%

    No Known Activations