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

    Neuronpedia

    INDEX
    Explanations

    encourage consistent nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Чу
    0.76
    baarheid
    0.73
    jitter
    0.69
    toluene
    0.65
    өө
    0.64
     Life
    0.63
     போட்டு
    0.62
     Wage
    0.62
    Tm
    0.62
    semp
    0.61
    POSITIVE LOGITS
    賑
    0.72
     हरा
    0.70
    ced
    0.70
     Kano
    0.70
    親子
    0.69
    鋐
    0.68
    紥
    0.67
     complaints
    0.67
     complains
    0.66
    ┅
    0.65
    Act Density 0.000%

    No Known Activations