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

    Neuronpedia

    INDEX
    Explanations

    potential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ordinal
    -0.08
     Concert
    -0.07
     виконав
    -0.07
    输入
    -0.06
     ions
    -0.06
     MSC
    -0.06
     spectra
    -0.06
    ﾏ
    -0.06
     abandonment
    -0.06
     Eş
    -0.06
    POSITIVE LOGITS
     farklı
    0.07
     entrance
    0.07
    拥
    0.07
    皆
    0.07
    decl
    0.07
     comparable
    0.06
    ueblo
    0.06
     Bunny
    0.06
     humble
    0.06
     Spanish
    0.06
    Act Density 0.016%

    No Known Activations