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

    Neuronpedia

    INDEX
    Explanations

    right. you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تمع
    0.68
     než
    0.68
    ezza
    0.65
     dua
    0.63
     torso
    0.61
    chievement
    0.60
     salto
    0.60
     tipo
    0.59
    ZIONE
    0.58
     vicino
    0.58
    POSITIVE LOGITS
    onate
    0.73
    imilar
    0.68
    нете
    0.66
    chemic
    0.65
    chr
    0.65
     бота
    0.65
     стран
    0.65
    ্থিত
    0.65
    اع
    0.64
    पीय
    0.64
    Act Density 0.001%

    No Known Activations