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

    Neuronpedia

    INDEX
    Explanations

    0 or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peaked
    -0.08
     Comments
    -0.07
     meaningful
    -0.07
     skip
    -0.07
    但是对于
    -0.07
    CONTENT
    -0.07
    也曾
    -0.06
     н
    -0.06
    _descriptor
    -0.06
    ",'
    -0.06
    POSITIVE LOGITS
    ┎
    0.07
     SolidColorBrush
    0.07
    ≫
    0.07
    THOOK
    0.07
    دع
    0.07
    Seconds
    0.07
    ALAR
    0.07
    elda
    0.07
    ovolta
    0.06
     mkdir
    0.06
    Act Density 0.011%

    No Known Activations