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

    Neuronpedia

    INDEX
    Explanations

    specific names and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.67
    m
    0.59
    l
    0.59
    v
    0.58
    z
    0.52
    an
    0.52
    p
    0.52
    g
    0.52
    S
    0.51
    al
    0.50
    POSITIVE LOGITS
     ridicu
    0.57
     formules
    0.52
     মূল্যবান
    0.51
     artículos
    0.50
     facteur
    0.48
     effets
    0.48
     maravilloso
    0.48
     وهذا
    0.47
     trolls
    0.47
     Maintenant
    0.47
    Act Density 0.002%

    No Known Activations