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

    Neuronpedia

    INDEX
    Explanations

    What

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('^
    -0.07
    mine
    -0.06
     badge
    -0.06
     drive
    -0.06
     зависимости
    -0.06
    [href
    -0.06
     Continuing
    -0.06
    radio
    -0.06
     dictionaries
    -0.06
    Save
    -0.06
    POSITIVE LOGITS
    _inp
    0.07
    ニック
    0.06
    ounces
    0.06
    _IMP
    0.06
    едаг
    0.06
    �
    0.06
    erties
    0.06
     صرف
    0.06
     unicode
    0.06
    경
    0.06
    Act Density 0.011%

    No Known Activations