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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fulness
    -0.07
    核定
    -0.07
    ุ
    -0.06
    �
    -0.06
    buch
    -0.06
     Giul
    -0.06
    温室
    -0.06
    陌
    -0.06
    隅
    -0.06
    蹙
    -0.06
    POSITIVE LOGITS
     exposition
    0.08
    )],
    0.08
    钱币
    0.08
    .ps
    0.07
    .capitalize
    0.07
     {},
    0.07
     scl
    0.07
    Christmas
    0.07
    amo
    0.07
    답
    0.06
    Act Density 0.004%

    No Known Activations