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

    Neuronpedia

    INDEX
    Explanations

    listing and information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ксана
    0.72
    LECTION
    0.58
    CODE
    0.57
    >
    0.56
     to
    0.55
     lymph
    0.55
     at
    0.54
     equival
    0.53
    -
    0.52
    ეგის
    0.52
    POSITIVE LOGITS
    t
    0.87
    n
    0.86
    ش
    0.85
    a
    0.84
    la
    0.83
    е
    0.82
    early
    0.81
    se
    0.81
    ru
    0.80
    ن
    0.80
    Act Density 0.000%

    No Known Activations