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

    Neuronpedia

    INDEX
    Explanations

    thinking of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Compare
    0.50
     Compare
    0.45
    compare
    0.42
     сорти
    0.42
    Comparer
    0.42
    Quanto
    0.41
    ochem
    0.40
    xSpeed
    0.39
     Mosley
    0.39
    Listo
    0.39
    POSITIVE LOGITS
     هنا
    0.43
    êmement
    0.43
    engah
    0.41
    êm
    0.41
     incarcerated
    0.40
     gong
    0.40
    эння
    0.39
    穢
    0.39
     ત્યાં
    0.39
    鳧
    0.39
    Act Density 0.007%

    No Known Activations