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

    Neuronpedia

    INDEX
    Explanations

    circumcised or toddle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.56
    ים
    0.50
     Sutter
    0.49
     Fastest
    0.48
    ओं
    0.48
     Best
    0.47
     نح
    0.47
    </em>
    0.45
     Sask
    0.44
     Soft
    0.44
    POSITIVE LOGITS
    中央
    0.52
    يك
    0.51
    穏
    0.50
    Η
    0.50
     coalgebras
    0.49
     éta
    0.47
    ೂರು
    0.47
    n
    0.46
    堭
    0.46
    дра
    0.46
    Act Density 0.000%

    No Known Activations