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

    Neuronpedia

    INDEX
    Explanations

    dates and time ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പഴയ
    0.44
     রাখবে
    0.39
     பழைய
    0.39
    Vas
    0.38
    0.38
     পুরাতন
    0.37
    yss
    0.37
    原有
    0.36
    魁
    0.36
     управления
    0.36
    POSITIVE LOGITS
     censoring
    0.46
     présent
    0.44
     gravid
    0.43
    Jetzt
    0.43
     interrog
    0.42
     jelen
    0.42
     saat
    0.41
     Cannes
    0.41
     currentPage
    0.40
     présentes
    0.40
    Act Density 0.037%

    No Known Activations