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

    Neuronpedia

    INDEX
    Explanations

    external support, funding, interests, factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ية
    0.70
    يد
    0.54
     was
    0.50
    }",
    0.50
     of
    0.49
     desempen
    0.48
    我们
    0.48
    其他
    0.48
    値
    0.48
     về
    0.47
    POSITIVE LOGITS
    External
    0.80
     External
    0.78
     external
    0.77
    n
    0.71
    external
    0.68
     외부
    0.65
    h
    0.61
    s
    0.60
     externes
    0.59
    int
    0.57
    Act Density 0.019%

    No Known Activations