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

    Neuronpedia

    INDEX
    Explanations

    honeyed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     불구하고
    1.03
     acidosis
    0.90
    િંગ
    0.90
    কাতার
    0.87
     teaspoons
    0.87
     onBackPressed
    0.86
    boiled
    0.84
    তিক্রম
    0.84
    ใส่
    0.83
    ला
    0.83
    POSITIVE LOGITS
    0.91
    ક
    0.90
    খ
    0.89
    ва
    0.83
    itude
    0.82
    s
    0.82
    ில்
    0.81
    sau
    0.80
    sale
    0.79
    народ
    0.79
    Act Density 0.002%

    No Known Activations