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

    Neuronpedia

    INDEX
    Explanations

    references to different types of models and programs

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

    types of models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     damn
    -0.38
    ToRead
    -0.32
     author
    -0.31
    </s>
    -0.31
     children
    -0.30
     DAMN
    -0.30
     Decorative
    -0.30
     getChild
    -0.29
     getUser
    -0.28
    getFile
    -0.28
    POSITIVE LOGITS
    complexContent
    0.88
     modello
    0.83
    modèle
    0.81
     '\\;'
    0.80
    modelBuilder
    0.79
     HasFactory
    0.77
     model
    0.74
     autorytatywna
    0.73
     AssemblyCulture
    0.73
     Modelle
    0.73
    Act Density 0.023%

    No Known Activations