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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ивши
    -0.06
    cılar
    -0.06
     себе
    -0.06
     gums
    -0.06
    escal
    -0.06
     NUIT
    -0.06
    yslu
    -0.06
     witch
    -0.06
     cyber
    -0.06
    持ち
    -0.06
    POSITIVE LOGITS
    0
    0.08
     オ
    0.07
     О
    0.07
     Dept
    0.07
     deported
    0.07
     abort
    0.07
    onent
    0.07
     Ø
    0.07
    PRECATED
    0.06
    .Q
    0.06
    Act Density 0.014%

    No Known Activations