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

    Neuronpedia

    INDEX
    Explanations

    hour

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hour
    -2.45
     Hour
    -2.08
    hour
    -2.00
     HOUR
    -1.92
    Hour
    -1.82
    HOUR
    -1.45
     hours
    -1.44
     Hours
    -1.34
     Stunde
    -1.30
     HOURS
    -1.23
    POSITIVE LOGITS
    '
    0.58
    (
    0.57
    ’
    0.49
    .
    0.46
    3
    0.42
    single
    0.41
    ↵
    0.41
    ↵↵
    0.41
     single
    0.41
     or
    0.40
    Act Density 0.054%

    No Known Activations