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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    verter
    -0.07
    muş
    -0.06
    서비스
    -0.06
    档
    -0.06
     Dropout
    -0.06
     discounts
    -0.06
    Outside
    -0.06
    _SETTINGS
    -0.06
    _compile
    -0.06
    .All
    -0.06
    POSITIVE LOGITS
     представляет
    0.07
    InstanceOf
    0.07
    큇
    0.07
    las
    0.07
    斤
    0.07
     Paris
    0.07
    期刊
    0.07
     Preferences
    0.07
     Exxon
    0.06
    _detected
    0.06
    Act Density 0.006%

    No Known Activations