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

    Neuronpedia

    INDEX
    Explanations

    timestamps and colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hour
    0.71
     hours
    0.64
     Hour
    0.61
     ساعت
    0.58
     horas
    0.57
     Hours
    0.57
     часа
    0.57
    hour
    0.57
     godziny
    0.56
    hours
    0.56
    POSITIVE LOGITS
     응
    0.45
    Ін
    0.40
     RESPONSE
    0.40
    鉀
    0.39
    RESPONSE
    0.39
    응
    0.38
    ianum
    0.37
    惻
    0.37
    iamiento
    0.36
     Antioxid
    0.36
    Act Density 0.000%

    No Known Activations