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

    Neuronpedia

    INDEX
    Explanations

    .com domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     first
    0.71
    장의
    0.58
    :")
    0.58
    রির
    0.58
     below
    0.58
    voorbeeld
    0.58
     FIRST
    0.58
     භාවිත
    0.57
    first
    0.57
    }^{+}$,
    0.55
    POSITIVE LOGITS
    Would
    1.03
     Would
    0.98
     quería
    0.95
    Does
    0.94
    org
    0.94
     semoga
    0.93
     Semoga
    0.92
     Does
    0.92
     Is
    0.91
    আমি
    0.89
    Act Density 0.066%

    No Known Activations