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

    Neuronpedia

    INDEX
    Explanations

    way more, too, above

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.94
    р
    0.84
    지만
    0.82
    защи
    0.79
    ر
    0.78
    나
    0.78
    во
    0.77
    il
    0.76
    про
    0.75
    ون
    0.75
    POSITIVE LOGITS
    ,
    0.86
    ının
    0.81
    ında
    0.76
    '
    0.75
    ına
    0.73
     dalla
    0.72
    ası
    0.69
     dan
    0.67
    ian
    0.66
    -
    0.66
    Act Density 0.052%

    No Known Activations