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

    Neuronpedia

    INDEX
    Explanations

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eca
    0.77
    gon
    0.77
     chips
    0.75
    apps
    0.70
     divid
    0.70
    PFA
    0.70
    chips
    0.70
    Split
    0.69
    t
    0.68
    ecta
    0.67
    POSITIVE LOGITS
    йга
    0.82
     уйнарга
    0.80
     vyš
    0.79
     μας
    0.78
     فانه
    0.76
    ﻳ
    0.76
    涞
    0.76
     मिळाली
    0.75
    磴
    0.75
     Согласно
    0.74
    Act Density 0.000%

    No Known Activations