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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yun
    -0.06
    icot
    -0.06
     studying
    -0.06
     politik
    -0.06
     guilty
    -0.06
    .Auth
    -0.06
     Parliamentary
    -0.06
     flown
    -0.06
     мень
    -0.06
     scanning
    -0.06
    POSITIVE LOGITS
    [e
    0.07
    VALUES
    0.07
    &gt
    0.07
    vě
    0.07
    コメント
    0.06
    @"
    0.06
    ')[
    0.06
     العربي
    0.06
    =>"
    0.06
     -:
    0.06
    Act Density 0.012%

    No Known Activations