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

    Neuronpedia

    INDEX
    Explanations

    PI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     지정
    -0.09
    .dist
    -0.08
     cenu
    -0.07
    zem
    -0.07
     closes
    -0.07
    xeb
    -0.07
    _OVER
    -0.06
     roam
    -0.06
    umas
    -0.06
    DEC
    -0.06
    POSITIVE LOGITS
     always
    0.07
    利
    0.07
    (QL
    0.07
    Normally
    0.07
    ัย
    0.07
     directly
    0.06
    -With
    0.06
    /GL
    0.06
    ß
    0.06
     Gr
    0.06
    Act Density 0.000%

    No Known Activations