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

    Neuronpedia

    INDEX
    Explanations

    sequential numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >∕
    0.47
    त्रेयी
    0.47
    opencamer
    0.46
     दमखम
    0.46
    ുകൊണ്ടാണ്
    0.45
    '`--'`--
    0.44
    衹
    0.44
    fireFlower
    0.43
    🏦
    0.43
    ائیگی
    0.43
    POSITIVE LOGITS
     =
    0.63
     N
    0.60
    0.60
     -
    0.57
     O
    0.57
    ↵
    0.55
    L
    0.55
    D
    0.54
    N
    0.54
    O
    0.54
    Act Density 0.000%

    No Known Activations