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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and notation

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

    Mathematical/statistical notation

    np_acts-logits-general · gemini-2.0-flash

    $\gamma$ and $\lambda$ estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.74
    -0.67
     cherchés
    -0.61
    uxxxx
    -0.58
     Мексичка
    -0.57
    transQ
    -0.56
    tanleria
    -0.56
     ویکی‌پدی
    -0.55
    rrggbb
    -0.55
    LookAnd
    -0.52
    POSITIVE LOGITS
     '/';
    0.47
     Zusch
    0.46
    <>();
    0.45
     Chamb
    0.42
     лай
    0.41
     autorytatywna
    0.40
     '/':
    0.40
     a
    0.40
     whose
    0.39
     ausgesch
    0.39
    Act Density 0.195%

    No Known Activations