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

    Neuronpedia

    INDEX
    Explanations

    simply have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    रा
    0.92
     are
    0.82
     compleja
    0.79
     cinética
    0.77
    ara
    0.75
    arians
    0.74
    ປະ
    0.73
     лиш
    0.71
     migraines
    0.71
    ारा
    0.70
    POSITIVE LOGITS
    ו
    1.08
    M
    0.91
    ку
    0.90
    of
    0.90
    و
    0.89
    T
    0.85
    L
    0.84
    G
    0.84
    Y
    0.82
    for
    0.81
    Act Density 0.000%

    No Known Activations