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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drink
    -0.07
    _over
    -0.07
    буд
    -0.06
    기를
    -0.06
    _safe
    -0.06
    $class
    -0.06
    스트
    -0.06
    �
    -0.06
    كام
    -0.06
     BaseController
    -0.06
    POSITIVE LOGITS
    าธ
    0.07
    ecektir
    0.06
     infos
    0.06
     Diagnostic
    0.06
    .FloatTensor
    0.06
    .ToDecimal
    0.06
    )\<
    0.06
    AMY
    0.06
     Hol
    0.06
     Sug
    0.06
    Act Density 0.013%

    No Known Activations