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

    Neuronpedia

    INDEX
    Explanations

    especially if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    В
    0.49
    С
    0.46
    늄
    0.45
    Д
    0.44
    К
    0.44
    P
    0.43
    ни
    0.43
    0.43
     distill
    0.43
    ↵↵
    0.42
    POSITIVE LOGITS
    رى
    0.49
    颀
    0.48
    സമയം
    0.47
    সমান
    0.47
    expr
    0.46
    sofar
    0.46
     avevano
    0.46
    وسیع
    0.46
    examtype
    0.45
    ᙱ
    0.45
    Act Density 0.004%

    No Known Activations