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

    Neuronpedia

    INDEX
    Explanations

    temporal units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posti
    0.56
    lapping
    0.55
    πάν
    0.52
    ரச
    0.52
    typing
    0.52
    udarstvennyj
    0.52
    licky
    0.51
    ropoda
    0.51
    रीबन
    0.50
    ப்படு
    0.49
    POSITIVE LOGITS
     week
    4.63
     month
    4.19
    week
    3.85
     weeks
    3.58
     semaine
    3.56
    month
    3.54
     Week
    3.50
    Week
    3.47
     Month
    3.45
     semana
    3.43
    Act Density 0.143%

    No Known Activations