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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *num
    -0.06
     επ
    -0.06
    374
    -0.06
     القرن
    -0.06
    ohen
    -0.06
    163
    -0.06
    array
    -0.06
    326
    -0.06
     ה
    -0.06
    ayer
    -0.06
    POSITIVE LOGITS
     painfully
    0.07
    、“
    0.07
     occupies
    0.07
    >{"
    0.07
     RX
    0.07
    .inspect
    0.07
    ..
    0.07
    (Api
    0.06
     Council
    0.06
     Norse
    0.06
    Act Density 0.015%

    No Known Activations