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

    Neuronpedia

    INDEX
    Explanations

    time durations like seconds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wl
    0.73
    ও
    0.73
     was
    0.69
    herent
    0.69
    :
    0.69
     infections
    0.68
     coolers
    0.68
     innervation
    0.68
    ;
    0.68
     hoses
    0.68
    POSITIVE LOGITS
    м
    0.91
    seconds
    0.90
     minutos
    0.89
    秒
    0.87
     minuto
    0.86
     segundos
    0.83
     instante
    0.83
     मिनट
    0.82
     秒
    0.82
     Sekunden
    0.80
    Act Density 0.145%

    No Known Activations