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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     péd
    0.81
     planète
    0.72
     formée
    0.71
     elbow
    0.70
    ilesh
    0.68
    ⵥ
    0.68
    भद्र
    0.68
     mortalidad
    0.67
    ಮ್ಮೆ
    0.67
     determinada
    0.67
    POSITIVE LOGITS
    ”:
    0.67
    стри
    0.67
    (":
    0.65
    stops
    0.64
     Orient
    0.62
    stop
    0.62
    ステー
    0.61
    MTV
    0.61
    乐趣
    0.60
    βέρ
    0.60
    Act Density 0.009%

    No Known Activations