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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to API documentation and method definitions

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

    Code, programming, and non-English text

    np_acts-logits-general · gemini-2.0-flash

    copyright and reproduction notices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fly
    -0.56
     AppCompatTheme
    -0.56
    UrlResolution
    -0.55
     Combien
    -0.52
    ize
    -0.49
    hdi
    -0.49
     باخ
    -0.48
    iasaan
    -0.48
    Lesen
    -0.48
     termica
    -0.48
    POSITIVE LOGITS
    Билгалдахарш
    0.62
    发表于
    0.60
    <bos>
    0.59
    verwijspagina
    0.58
    COUVER
    0.56
     Exacts
    0.54
    complexContent
    0.54
    AutoScaleMode
    0.53
    ValueStyle
    0.52
    serviceWorker
    0.51
    Act Density 0.058%

    No Known Activations