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

    Neuronpedia

    INDEX
    Explanations

    polskie czasowniki i przymiotniki

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鹖
    0.41
    ंका
    0.39
    ändigen
    0.38
    গারে
    0.38
    lah
    0.38
    수인
    0.37
    LAH
    0.37
    اتے
    0.37
     complicate
    0.37
     ক্লে
    0.36
    POSITIVE LOGITS
    zy
    0.95
    zenie
    0.91
    sz
    0.86
    zenia
    0.85
    z
    0.82
    ze
    0.80
    rz
    0.78
    zeczy
    0.78
    zé
    0.78
    zz
    0.75
    Act Density 0.002%

    No Known Activations