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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and implementation details

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

    TensorFlow code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DoubleQuotes
    -0.81
    TypedDataSet
    -0.77
     Infórmanos
    -0.68
    EDEFAULT
    -0.62
    AddTagHelper
    -0.62
    seteq
    -0.60
    TemporalType
    -0.59
    IntoConstraints
    -0.59
    UnsafeEnabled
    -0.59
     surla
    -0.56
    POSITIVE LOGITS
     tf
    0.52
    tf
    0.40
     LAMB
    0.30
     hits
    0.28
     par
    0.28
    pf
    0.28
     haya
    0.27
     legalization
    0.27
    Ram
    0.27
    Gen
    0.27
    Act Density 0.004%

    No Known Activations