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

    Neuronpedia

    INDEX
    Explanations

    consequences and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    伱
    0.87
     remarkably
    0.87
     quite
    0.86
    :\
    0.84
    ']):
    0.81
    :</
    0.81
     largely
    0.81
     considerably
    0.80
     noticeably
    0.80
     striving
    0.78
    POSITIVE LOGITS
     "
    1.48
     “
    1.40
     "",
    1.38
    ?,
    1.35
     якобы
    1.33
     "...
    1.32
     ",
    1.30
     blah
    1.27
     "'
    1.25
     "-",
    1.23
    Act Density 0.020%

    No Known Activations