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

    Neuronpedia

    INDEX
    Explanations

    button and "or" words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     বলিয়াই
    0.45
     OSX
    0.36
     patitth
    0.36
    uire
    0.34
    ensk
    0.33
    recated
    0.33
    गेशन
    0.33
    ience
    0.33
    Pn
    0.32
    ieza
    0.32
    POSITIVE LOGITS
     alebo
    0.36
     किंवा
    0.34
    漪
    0.32
     లేదా
    0.32
     또는
    0.31
     અથવા
    0.31
     своя
    0.31
    หรือ
    0.30
     или
    0.30
     או
    0.29
    Act Density 0.000%

    No Known Activations