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

    Neuronpedia

    INDEX
    Explanations

    CNN

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _proof
    -0.08
    urbed
    -0.07
    古
    -0.07
     french
    -0.07
    槁
    -0.07
    名列前茅
    -0.07
    biology
    -0.07
    .coll
    -0.07
    foods
    -0.07
    ENCHMARK
    -0.07
    POSITIVE LOGITS
    红旗
    0.07
     wij
    0.07
    担当
    0.07
     speakers
    0.07
     ------
    0.07
     résultats
    0.07
     siblings
    0.06
     incarcerated
    0.06
    China
    0.06
    安慰
    0.06
    Act Density 0.003%

    No Known Activations