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

    Neuronpedia

    INDEX
    Explanations

    all associated items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     모든
    1.94
     toate
    1.74
     semua
    1.60
     всички
    1.57
     सभी
    1.53
     toutes
    1.52
     todas
    1.51
     جميع
    1.47
     všetky
    1.46
    全ての
    1.46
    POSITIVE LOGITS
    igators
    0.97
     sorts
    0.95
     equally
    0.93
    uding
    0.92
     kinds
    0.89
     significantly
    0.88
    usions
    0.86
    antoin
    0.84
     vying
    0.83
     reluctantly
    0.83
    Act Density 0.021%

    No Known Activations