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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (r
    -0.07
    _ids
    -0.07
    FORM
    -0.07
    -enabled
    -0.06
    .Size
    -0.06
     ride
    -0.06
    isters
    -0.06
    _coverage
    -0.06
     argc
    -0.06
    :')
    -0.06
    POSITIVE LOGITS
     hely
    0.08
     توان
    0.07
     hüc
    0.06
     духов
    0.06
     crimson
    0.06
     servi
    0.06
     relev
    0.06
     uplift
    0.06
     SEARCH
    0.06
    kHz
    0.06
    Act Density 0.030%

    No Known Activations