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

    Neuronpedia

    INDEX
    Explanations

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giant
    -0.07
    .decorate
    -0.07
     monitor
    -0.07
    cisi
    -0.07
    ulti
    -0.06
    тами
    -0.06
    문의
    -0.06
    hx
    -0.06
     sním
    -0.06
    μένη
    -0.06
    POSITIVE LOGITS
     výstav
    0.06
    日期
    0.06
     navr
    0.06
     próp
    0.06
    _COL
    0.06
     раньше
    0.06
    ";
    0.06
    可是
    0.06
    _WEIGHT
    0.06
                               ↵
    0.06
    Act Density 0.014%

    No Known Activations