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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ர்
    2.14
    ून
    1.93
    ura
    1.90
    ல்
    1.89
     tamaños
    1.88
    ía
    1.86
     estoy
    1.84
    piece
    1.84
    sc
    1.82
    uff
    1.81
    POSITIVE LOGITS
    ש
    2.14
    ا
    1.96
    ೆ
    1.95
    ت
    1.91
     Retry
    1.80
    га
    1.75
    ੍ਹ
    1.72
     Dup
    1.70
    ❤❤
    1.70
     Hp
    1.69
    Act Density 0.110%

    No Known Activations