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

    Neuronpedia

    INDEX
    Explanations

    AI algorithms and their impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emboss
    0.47
    lins
    0.47
     Giveen
    0.46
     subcellular
    0.45
     ईमित्र
    0.44
    User
    0.44
     Наталья
    0.43
    Ĕ
    0.43
    Serialize
    0.43
     હંમે
    0.43
    POSITIVE LOGITS
     τά
    0.57
     που
    0.48
     yang
    0.46
    στι
    0.45
     лу
    0.44
     di
    0.43
    ню
    0.43
     cao
    0.41
     குறை
    0.41
     natura
    0.41
    Act Density 0.003%

    No Known Activations