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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrayList
    -0.07
    dük
    -0.07
     interpolated
    -0.07
    ipl
    -0.07
    appe
    -0.07
    Dirs
    -0.07
    ерта
    -0.06
    かった
    -0.06
    ��
    -0.06
    angkan
    -0.06
    POSITIVE LOGITS
     costly
    0.07
    _OVERFLOW
    0.07
    MER
    0.06
    _dim
    0.06
    _bases
    0.06
    testdata
    0.06
    „J
    0.06
    .raises
    0.06
     Hum
    0.06
    _man
    0.06
    Act Density 0.056%

    No Known Activations