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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    充满了
    -0.08
     unitOfWork
    -0.07
     луч
    -0.07
     brunch
    -0.07
    Allows
    -0.07
     Nicar
    -0.07
     portrayal
    -0.07
     turnovers
    -0.06
    .settings
    -0.06
    ilan
    -0.06
    POSITIVE LOGITS
    浆
    0.07
    及
    0.07
    蹈
    0.07
     whose
    0.07
    ➾
    0.07
    RGBO
    0.06
    LIKELY
    0.06
    MouseEvent
    0.06
     Regex
    0.06
     ks
    0.06
    Act Density 0.042%

    No Known Activations