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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dü
    -0.07
     poc
    -0.07
    把你
    -0.06
    往来
    -0.06
    issuer
    -0.06
     ECC
    -0.06
    上年
    -0.06
     collapses
    -0.06
    לית
    -0.06
    废弃
    -0.06
    POSITIVE LOGITS
    �
    0.07
    :request
    0.07
    dıklar
    0.07
     Problems
    0.07
    휘
    0.07
    퇘
    0.07
    _Private
    0.07
    olic
    0.07
    inheritDoc
    0.07
     undermin
    0.07
    Act Density 0.002%

    No Known Activations