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

    Neuronpedia

    INDEX
    Explanations

    time in hours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     त्रिदेव
    0.60
     aque
    0.58
     deven
    0.57
    ティブ
    0.57
    释
    0.57
    vald
    0.56
    ائنات
    0.56
    snippets
    0.55
     судь
    0.55
    年初
    0.55
    POSITIVE LOGITS
     hours
    4.83
     hour
    4.82
     Hours
    4.38
    hours
    4.36
    hour
    4.35
    Hours
    4.22
     Hour
    4.04
    Hour
    4.03
     horas
    3.91
     HOURS
    3.78
    Act Density 0.520%

    No Known Activations