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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .nickname
    -0.07
     noon
    -0.06
     Bent
    -0.06
     Independence
    -0.06
    刀
    -0.06
     repay
    -0.06
     XCTestCase
    -0.06
    .findall
    -0.06
     spent
    -0.06
     imped
    -0.06
    POSITIVE LOGITS
     artık
    0.07
    prech
    0.07
    _embedding
    0.07
    riterion
    0.07
    าพ
    0.07
    recated
    0.06
     hangi
    0.06
     transcription
    0.06
    topl
    0.06
    Guid
    0.06
    Act Density 0.002%

    No Known Activations