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

    Neuronpedia

    INDEX
    Explanations

    SAMHSA National Helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Every
    0.87
     każdy
    0.85
     Everyone
    0.84
     świecie
    0.83
     શેર
    0.82
     "...
    0.81
     Query
    0.79
    нями
    0.78
    <0xC4>
    0.78
    Everyone
    0.77
    POSITIVE LOGITS
    తీ
    0.84
     enhance
    0.81
    サ
    0.77
    ホール
    0.76
    রন
    0.75
     enhancements
    0.75
     nâng
    0.73
    örder
    0.73
     liability
    0.73
    सा
    0.73
    Act Density 0.093%

    No Known Activations