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

    Neuronpedia

    INDEX
    Explanations

    inplace=True

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esteja
    0.92
     encontrará
    0.88
    인더
    0.88
     empê
    0.86
     zależ
    0.85
    Се
    0.84
     către
    0.83
     ért
    0.80
     Sprachen
    0.80
     želite
    0.80
    POSITIVE LOGITS
    al
    0.98
    er
    0.91
    day
    0.86
    /=
    0.82
    achusetts
    0.77
    price
    0.76
    etown
    0.76
    しない
    0.75
    ا
    0.75
    rement
    0.74
    Act Density 0.000%

    No Known Activations