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

    Neuronpedia

    INDEX
    Explanations

    ATT&CK framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    它
    0.80
    I
    0.77
    padă
    0.72
    ="
    0.67
    였다
    0.65
    เล
    0.65
    ))
    0.64
    <0x83>
    0.63
     atau
    0.62
     engineer
    0.62
    POSITIVE LOGITS
     on
    1.30
    r
    1.25
    on
    0.98
    7
    0.91
    t
    0.88
     ऑन
    0.86
    ب
    0.84
    ৬
    0.84
    ت
    0.83
    1
    0.82
    Act Density 0.001%

    No Known Activations