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

    Neuronpedia

    INDEX
    Explanations

    stuck in a situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x80>
    0.91
    ные
    0.77
    стью
    0.75
    ра
    0.75
    E
    0.75
    тер
    0.74
    чки
    0.72
    тов
    0.71
    вана
    0.70
    ;
    0.70
    POSITIVE LOGITS
    م
    0.98
     फं
    0.79
    ه
    0.78
    dos
    0.72
     stranded
    0.72
     অবস্থা
    0.71
    0.71
     फंस
    0.70
     समय
    0.69
     पर
    0.69
    Act Density 0.011%

    No Known Activations