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

    Neuronpedia

    INDEX
    Explanations

    C# collections in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    1.04
    F
    0.95
    1
    0.93
    9
    0.91
    K
    0.90
    4
    0.88
    >
    0.85
    H
    0.80
    You
    0.79
    6
    0.77
    POSITIVE LOGITS
    ла
    0.69
    л
    0.66
     condiv
    0.65
    as
    0.64
    𒌉
    0.63
    ్‌
    0.63
     አበባ
    0.63
     CHAS
    0.60
     superstructure
    0.60
    дной
    0.59
    Act Density 0.001%

    No Known Activations