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

    Neuronpedia

    INDEX
    Explanations

    technical terms and devices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Phát
    0.63
     Conoc
    0.58
     Nuest
    0.56
     Tạo
    0.55
     वेरिए
    0.55
     ပြော
    0.54
     Una
    0.52
     Aqui
    0.52
     También
    0.52
     Otros
    0.52
    POSITIVE LOGITS
    ﺍ
    0.39
    Ι
    0.39
    fruits
    0.38
    ｸ
    0.38
    IV
    0.38
    Be
    0.38
     fruits
    0.37
    evil
    0.37
    ｳ
    0.37
     legumes
    0.37
    Act Density 0.001%

    No Known Activations