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

    Neuronpedia

    INDEX
    Explanations

    perf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    볼
    -0.07
    ulen
    -0.07
    _PUS
    -0.07
    item
    -0.06
    ывают
    -0.06
     house
    -0.06
    Stan
    -0.06
    kol
    -0.06
     mutex
    -0.06
    agus
    -0.06
    POSITIVE LOGITS
     perf
    0.12
     PERF
    0.09
     bf
    0.07
     Surf
    0.07
     EFI
    0.07
    perf
    0.07
    iễ
    0.07
    с
    0.07
    ifi
    0.07
     ventil
    0.07
    Act Density 0.002%

    No Known Activations