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

    Neuronpedia

    INDEX
    Explanations

    factors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    来了
    -0.07
     приня
    -0.07
    опрос
    -0.06
    pecies
    -0.06
    ريط
    -0.06
     영어
    -0.06
    以
    -0.06
    pres
    -0.06
    _primary
    -0.06
    圈
    -0.06
    POSITIVE LOGITS
     warns
    0.07
    _TERM
    0.07
     emblem
    0.06
    .contents
    0.06
    .ST
    0.06
    ็นท
    0.06
    imd
    0.06
    .non
    0.06
    992
    0.06
     технолог
    0.06
    Act Density 0.001%

    No Known Activations