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

    Neuronpedia

    INDEX
    Explanations

    vector

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pst
    -0.08
     Marathon
    -0.07
    _PIN
    -0.07
     adjustments
    -0.07
    要注意
    -0.07
    にお
    -0.07
    参赛
    -0.07
    =z
    -0.07
     anc
    -0.07
    スペ
    -0.07
    POSITIVE LOGITS
    mówi
    0.08
    罕
    0.08
    王晓
    0.07
    ורים
    0.07
    -MM
    0.07
     Crab
    0.07
    ernen
    0.07
    ungalow
    0.07
     W
    0.07
    ophysical
    0.07
    Act Density 0.006%

    No Known Activations