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

    Neuronpedia

    INDEX
    Explanations

    electrical circuits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Andal
    -0.08
     murders
    -0.08
    Insurance
    -0.08
     tat
    -0.07
     rows
    -0.07
     crimes
    -0.07
    地图
    -0.07
     individuality
    -0.07
     duplicated
    -0.07
    Arabic
    -0.07
    POSITIVE LOGITS
     impedance
    0.12
     холод
    0.09
     Frequency
    0.09
    oloji
    0.08
     Hank
    0.08
     fft
    0.08
     sinus
    0.08
    ตอบ
    0.08
     hostile
    0.08
     الليل
    0.08
    Act Density 0.004%

    No Known Activations