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

    Neuronpedia

    INDEX
    Explanations

    view Models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.71
    G
    0.70
    R
    0.67
    F
    0.63
    J
    0.63
    C
    0.61
    IN
    0.61
    CH
    0.57
    EN
    0.56
     г
    0.56
    POSITIVE LOGITS
    した
    0.73
    лика
    0.71
    StarCore
    0.66
     Prothorax
    0.66
    kan
    0.66
    ায়ন
    0.63
    ഽ
    0.62
    ком
    0.61
    ку
    0.61
    вача
    0.61
    Act Density 0.000%

    No Known Activations