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

    Neuronpedia

    INDEX
    Explanations

    Pastebin, compared, rapidly, AS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     colorido
    0.91
     говорится
    0.82
     poderes
    0.79
     ۸
    0.79
     इंजीनियरिंग
    0.79
     Liên
    0.79
    bücher
    0.78
     nacionales
    0.77
     geometri
    0.77
    Ⲱ
    0.77
    POSITIVE LOGITS
    esque
    0.85
    In
    0.79
    Id
    0.79
    Legacy
    0.78
    },
    0.76
    Chief
    0.76
    ="
    0.76
    .
    0.75
    get
    0.75
    Im
    0.75
    Act Density 0.000%

    No Known Activations