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

    Neuronpedia

    INDEX
    Explanations

    diverse scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     veces
    0.71
     lebens
    0.70
     enseñ
    0.69
     guerras
    0.69
     Mesmo
    0.68
     organs
    0.65
     melodies
    0.65
     Bete
    0.65
     mitte
    0.65
    splitLength
    0.65
    POSITIVE LOGITS
    y
    1.25
    ه
    1.11
    ن
    1.00
    l
    0.98
    ו
    0.97
    ン
    0.96
    ০
    0.95
    z
    0.92
    o
    0.91
    一个
    0.90
    Act Density 2.242%

    No Known Activations