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

    Neuronpedia

    INDEX
    Explanations

    quotations and example phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     எனப்படும்
    0.47
    と呼ばれる
    0.44
    \...
    0.42
    >();
    0.38
     residing
    0.38
    >::
    0.37
    (...)
    0.37
    '])[
    0.36
    ()];
    0.36
    aceutical
    0.36
    POSITIVE LOGITS
     ‘
    1.82
     “
    1.73
     "
    1.65
     '
    1.54
     「
    1.47
     «
    1.39
    「
    1.34
     “‘
    1.34
     `
    1.24
     `"
    1.23
    Act Density 0.319%

    No Known Activations