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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and parentheses

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

    parenthetical phrases and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ruf
    -0.36
    URLException
    -0.35
     Ruf
    -0.34
    想到
    -0.34
    Errorf
    -0.31
    MÁS
    -0.31
    Offset
    -0.29
    地看着
    -0.29
    fristig
    -0.29
     دف
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.86
    LookAnd
    0.65
    UnusedPrivate
    0.63
    脚注の使い方
    0.62
    PerformLayout
    0.59
    IntoConstraints
    0.59
     autorytatywna
    0.58
     GenerationType
    0.56
    MLLoader
    0.56
    PreInfinity
    0.56
    Act Density 0.053%

    No Known Activations