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

    Neuronpedia

    INDEX
    Explanations

    process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DIRECT
    -0.07
     другой
    -0.07
    ной
    -0.06
    から
    -0.06
    Browse
    -0.06
     sứ
    -0.06
    masters
    -0.06
    ीप
    -0.06
    배
    -0.06
    леж
    -0.06
    POSITIVE LOGITS
     Fighter
    0.07
     Flush
    0.07
    (Equal
    0.06
    ,msg
    0.06
     __(
    0.06
     अद
    0.06
     Marcel
    0.06
    災
    0.06
     Mare
    0.06
     induced
    0.06
    Act Density 0.041%

    No Known Activations