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

    Neuronpedia

    INDEX
    Explanations

    date: month day year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mécanismes
    0.46
    ResBuffer
    0.42
     রব
    0.40
    Bootstrap
    0.37
    бур
    0.36
     macromolecules
    0.36
    Invoke
    0.36
    थन
    0.35
    Pane
    0.35
     equação
    0.35
    POSITIVE LOGITS
     fecha
    0.98
     October
    0.97
     date
    0.91
     November
    0.88
     February
    0.84
    日期
    0.84
     Fecha
    0.84
     September
    0.83
     Date
    0.82
    Fecha
    0.81
    Act Density 0.048%

    No Known Activations