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

    Neuronpedia

    INDEX
    Explanations

    instances of code snippets or programming blocks

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

    code structures and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۗ
    -0.44
    huana
    -0.42
     strtok
    -0.41
    zionalità
    -0.41
    ánchez
    -0.39
    vcut
    -0.39
     butterknife
    -0.38
     faune
    -0.38
     sereia
    -0.37
     griechischen
    -0.37
    POSITIVE LOGITS
    \]
    1.00
    <bos>
    0.63
     مشين
    0.57
    Tikang
    0.55
    setVerticalGroup
    0.54
     iconLine
    0.54
    delwed
    0.52
    adpleegd
    0.52
    VersionUID
    0.50
    ContentLoaded
    0.49
    Act Density 0.018%

    No Known Activations