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

    Neuronpedia

    INDEX
    Explanations

    business terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    0.62
    u
    0.54
    math
    0.46
     आणि
    0.45
     relentless
    0.44
    and
    0.43
    spiration
    0.43
    o
    0.43
     and
    0.42
    ed
    0.42
    POSITIVE LOGITS
     或
    0.61
     или
    0.56
    或
    0.53
    หรือ
    0.48
     alebo
    0.47
     دارند
    0.46
     Asalamualaikum
    0.46
     veya
    0.45
     หรือ
    0.44
    例えば
    0.44
    Act Density 0.006%

    No Known Activations