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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imizin
    -0.07
    结合
    -0.07
    _pdf
    -0.06
    вих
    -0.06
    (SP
    -0.06
    oord
    -0.06
     Saturdays
    -0.06
     flat
    -0.06
     XV
    -0.06
     сек
    -0.06
    POSITIVE LOGITS
    레이
    0.07
     информ
    0.07
     harmon
    0.06
    टन
    0.06
    ंस
    0.06
     wav
    0.06
     Daniels
    0.06
     Production
    0.06
    jejer
    0.06
     dysfunctional
    0.06
    Act Density 0.004%

    No Known Activations