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

    Neuronpedia

    INDEX
    Explanations

    philosophical discussions or training logs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     analytically
    0.38
    COL
    0.38
    AL
    0.38
    OL
    0.37
    J
    0.37
    AC
    0.36
     technical
    0.35
     QA
    0.35
     statistically
    0.35
    T
    0.35
    POSITIVE LOGITS
    աղ
    0.47
     Цент
    0.46
     Оста
    0.46
    Фе
    0.45
     bezpie
    0.45
     obnov
    0.45
     miejsce
    0.44
    തിക
    0.44
     дзяржа
    0.44
     серпня
    0.44
    Act Density 0.002%

    No Known Activations