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

    Neuronpedia

    INDEX
    Explanations

    LaTeX code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ◊
    -0.07
     -----------------------------------------------------------------------------↵
    -0.07
    _INCREF
    -0.07
    ohen
    -0.07
     nen
    -0.07
     JButton
    -0.07
    uddenly
    -0.07
     pä
    -0.07
    鹈
    -0.06
    textBox
    -0.06
    POSITIVE LOGITS
    艾滋
    0.08
    쪘
    0.08
     заказ
    0.07
    剁
    0.07
    Value
    0.07
    各类
    0.07
     settle
    0.07
     varieties
    0.07
    ickers
    0.07
     sentiments
    0.07
    Act Density 0.000%

    No Known Activations