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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ケース
    -0.08
    Images
    -0.07
    ังม
    -0.07
    USED
    -0.07
    rists
    -0.06
    eval
    -0.06
    _SCHED
    -0.06
     Easy
    -0.06
     suggesting
    -0.06
    判断
    -0.06
    POSITIVE LOGITS
     ได
    0.06
     необхідно
    0.06
    ichick
    0.06
    .Work
    0.06
     इल
    0.06
    call
    0.06
     sext
    0.06
     showcased
    0.06
     Tempo
    0.05
    "Our
    0.05
    Act Density 0.017%

    No Known Activations