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
     жовтня
    -0.06
     Christmas
    -0.06
     Occupation
    -0.06
    пов
    -0.06
    verter
    -0.06
    なければ
    -0.06
     outlining
    -0.06
     брат
    -0.06
    aterial
    -0.06
    Geometry
    -0.06
    POSITIVE LOGITS
    mux
    0.07
    _videos
    0.07
    engers
    0.07
    essenger
    0.07
     ší
    0.07
    duğu
    0.06
    .wind
    0.06
     Vanessa
    0.06
    林
    0.06
     Ath
    0.06
    Act Density 0.000%

    No Known Activations