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

    Neuronpedia

    INDEX
    Explanations

    copyright notices in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     găsit
    0.55
     adicion
    0.55
     combustível
    0.51
     equação
    0.50
     arkadaş
    0.50
    از
    0.49
     abelian
    0.49
     çiçek
    0.48
     administrativa
    0.48
     estadísticas
    0.48
    POSITIVE LOGITS
     (
    0.86
    (
    0.74
    ed
    0.69
     J
    0.59
    -
    0.58
     British
    0.56
     David
    0.55
     Ke
    0.54
    n
    0.54
    isn
    0.53
    Act Density 0.000%

    No Known Activations