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

    Neuronpedia

    INDEX
    Explanations

    content related to mathematical or statistical calculations

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

    Text within brackets or parentheses

    np_acts-logits-general · gemini-2.0-flash

    formulaic expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     super
    -0.96
    super
    -0.90
     Super
    -0.72
    Super
    -0.63
     SUPER
    -0.62
     супер
    -0.59
     súper
    -0.54
    超级
    -0.53
    SUPER
    -0.48
    مقدمه
    -0.46
    POSITIVE LOGITS
    boxed
    1.02
    makeConstraints
    1.00
    SourceChecksum
    0.97
    ConstraintMaker
    0.86
    EndContext
    0.82
    aarrggbb
    0.77
    underline
    0.76
     hymns
    0.72
    IntoConstraints
    0.72
    astify
    0.71
    Act Density 0.318%

    No Known Activations