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

    Neuronpedia

    INDEX
    Explanations

    multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    1.10
    THING
    0.81
    ς
    0.73
    ों
    0.73
    𝐬
    0.73
    nya
    0.73
    릭터
    0.73
    ا
    0.70
    ನ
    0.70
     pebbles
    0.68
    POSITIVE LOGITS
    zelfde
    1.23
    на
    1.04
    quele
    0.93
    ان
    0.91
    न
    0.84
     comenzaron
    0.81
    𝓻
    0.80
    л
    0.78
    ти
    0.77
    ğini
    0.76
    Act Density 0.818%

    No Known Activations