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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and structures

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

    math, science, and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.52
    ValueStyle
    -0.49
    contentLoaded
    -0.48
     Eſ
    -0.47
    SequentialGroup
    -0.46
    makeConstraints
    -0.43
    IsContent
    -0.42
    Personendaten
    -0.42
     ffilmiau
    -0.42
    millimeters
    -0.41
    POSITIVE LOGITS
    ValueGeneration
    0.43
     <<<<<<<<<<<<<<
    0.41
     ProtoMessage
    0.41
     Gaye
    0.40
    ptor
    0.40
     Hog
    0.40
    olor
    0.39
    TintMode
    0.39
    最快更新
    0.38
     returns
    0.38
    Act Density 0.120%

    No Known Activations