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

    Neuronpedia

    INDEX
    Explanations

    assessment of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.13
    jší
    1.09
    ästä
    1.09
    scht
    0.96
    し
    0.94
    ia
    0.94
    ä
    0.93
    ۹
    0.91
    ായ
    0.90
    \
    0.87
    POSITIVE LOGITS
    0
    1.71
    ０
    1.18
    <0x80>
    1.15
    ;
    1.04
     Assessment
    1.03
    म
    1.02
    ב
    1.02
    for
    0.98
     for
    0.97
    வ
    0.92
    Act Density 0.049%

    No Known Activations