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

    Neuronpedia

    INDEX
    Explanations

    planets in order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estándar
    0.47
    ség
    0.47
    k
    0.46
     primos
    0.45
     avec
    0.44
     với
    0.43
     límite
    0.43
     két
    0.43
     dengan
    0.43
     με
    0.43
    POSITIVE LOGITS
    9
    0.45
     The
    0.42
     Its
    0.41
    &
    0.40
    7
    0.39
    6
    0.39
     Casualty
    0.38
     இறுதியில்
    0.38
    形で
    0.36
     Piece
    0.36
    Act Density 1.736%

    No Known Activations