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

    Neuronpedia

    INDEX
    Explanations

    intervals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الشخص
    -0.08
    نيا
    -0.08
     شخصية
    -0.08
     concurso
    -0.08
    ichter
    -0.08
     ағ
    -0.07
     nhiều
    -0.07
     سنگ
    -0.07
     Complex
    -0.07
     complexion
    -0.07
    POSITIVE LOGITS
     uninterrupted
    0.10
     separated
    0.09
     wise
    0.09
     empty
    0.08
    별
    0.08
     intervals
    0.08
     subdivisions
    0.08
     unchecked
    0.07
     segments
    0.07
    .AP
    0.07
    Act Density 0.018%

    No Known Activations