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

    Neuronpedia

    INDEX
    Explanations

    (n = number)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =password
    -0.08
    (Func
    -0.07
    .Stream
    -0.07
    utf
    -0.07
     gpointer
    -0.06
     cụ
    -0.06
    sdale
    -0.06
    =M
    -0.06
    _TERM
    -0.06
     سرو
    -0.06
    POSITIVE LOGITS
     Related
    0.07
    trimmed
    0.06
    訂
    0.06
     حالة
    0.06
    대비
    0.06
     precedence
    0.06
    ्रध
    0.06
     legalize
    0.05
    .Encode
    0.05
     little
    0.05
    Act Density 0.033%

    No Known Activations