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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _once
    -0.06
    �
    -0.06
    -largest
    -0.06
    egade
    -0.06
    ू
    -0.06
     celebrated
    -0.06
     encuent
    -0.05
     khô
    -0.05
     portfolios
    -0.05
     fellow
    -0.05
    POSITIVE LOGITS
    _TEM
    0.07
    ющий
    0.07
     implicit
    0.07
    (rng
    0.07
    ren
    0.07
    тє
    0.06
     Перед
    0.06
     tercih
    0.06
    udoku
    0.06
    _prior
    0.06
    Act Density 0.000%

    No Known Activations