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

    Neuronpedia

    INDEX
    Explanations

    1-800-656-HOPE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ຖື
    0.83
    遗憾
    0.78
     राव
    0.76
    дание
    0.75
     برو
    0.73
    ద్య
    0.71
    غم
    0.70
    团结
    0.70
     заг
    0.70
    मारक
    0.70
    POSITIVE LOGITS
    ень
    0.73
    good
    0.71
     Good
    0.70
     good
    0.64
    ABASE
    0.63
     Paying
    0.63
     ABCD
    0.62
     bons
    0.62
     promos
    0.62
    promoting
    0.62
    Act Density 0.005%

    No Known Activations