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

    Neuronpedia

    INDEX
    Explanations

    group terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     missing
    0.47
    missing
    0.47
    ky
    0.45
    Missing
    0.44
     permukaan
    0.43
    react
    0.43
    luk
    0.42
     none
    0.42
    ž
    0.42
    plum
    0.42
    POSITIVE LOGITS
     становится
    0.46
     Ensures
    0.46
     организация
    0.43
    幼儿
    0.43
     organismes
    0.43
     becomes
    0.42
     nursery
    0.42
    INFRINGEMENT
    0.42
     devient
    0.42
     защиты
    0.42
    Act Density 0.008%

    No Known Activations