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

    Neuronpedia

    INDEX
    Explanations

    Sh words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.25
    is
    1.23
    를
    1.13
    的同时
    1.06
    ต
    1.05
    ّ
    1.04
    ội
    1.01
    的三
    1.01
    was
    0.98
    YA
    0.98
    POSITIVE LOGITS
    ב
    1.35
    ).
    1.30
    og
    1.21
     hurriedly
    1.20
    ।
    1.20
     controlar
    1.20
     mudar
    1.19
    ’
    1.19
     contrôle
    1.18
     torno
    1.17
    Act Density 0.291%

    No Known Activations