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

    Neuronpedia

    INDEX
    Explanations

    single quotes or double quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     king
    0.50
     ਨਾਲ
    0.50
     тексту
    0.50
     Safegu
    0.49
    ༔
    0.49
     with
    0.48
     fois
    0.48
     abruptly
    0.47
     lentamente
    0.46
     eux
    0.46
    POSITIVE LOGITS
    at
    0.66
    ncnc
    0.52
    equity
    0.51
    SRPI
    0.50
    he
    0.50
    remark
    0.49
     perfused
    0.49
    countries
    0.48
    collections
    0.48
    crops
    0.48
    Act Density 0.000%

    No Known Activations