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

    Neuronpedia

    INDEX
    Explanations

    error handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    otherwise
    1.58
    Otherwise
    1.55
     otherwise
    1.53
     Otherwise
    1.45
    否则
    1.38
     OTHERWISE
    1.30
     иначе
    1.20
     अन्यथा
    1.17
    不然
    1.10
     autrement
    0.90
    POSITIVE LOGITS
    或是
    1.16
     oder
    1.12
     Или
    1.11
     либо
    1.09
     elif
    1.08
    或者是
    1.07
     किंवा
    1.06
     或
    1.06
     eller
    1.06
     или
    1.06
    Act Density 0.076%

    No Known Activations