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

    Neuronpedia

    INDEX
    Explanations

    snakes, weapons, and monsters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지
    1.39
    ب
    1.23
    मा
    1.20
    रा
    1.14
    ции
    1.13
    де
    1.12
    <0x80>
    1.08
    و
    1.08
    ра
    1.07
    ما
    1.06
    POSITIVE LOGITS
    ’
    1.30
    -
    1.10
     l
    1.05
     an
    1.01
     on
    0.95
     y
    0.88
    '
    0.85
     r
    0.84
     U
    0.82
     that
    0.82
    Act Density 0.140%

    No Known Activations