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

    Neuronpedia

    INDEX
    Explanations

    dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     historians
    1.54
    elje
    1.45
    囝
    1.40
     dí
    1.39
    etzungen
    1.32
    佢
    1.32
    구를
    1.32
     entertained
    1.31
    แกรม
    1.30
    phasis
    1.30
    POSITIVE LOGITS
     September
    4.09
     July
    4.07
    July
    3.92
     November
    3.89
     April
    3.89
     August
    3.86
     June
    3.82
     January
    3.81
    September
    3.78
     December
    3.78
    Act Density 1.075%

    No Known Activations