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

    Neuronpedia

    INDEX
    Explanations

    standard way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    räge
    0.63
     réel
    0.60
     ספר
    0.60
     vliegt
    0.60
     Thời
    0.59
     পুস্ত
    0.57
    ௭
    0.57
    ঁচা
    0.57
     COc
    0.57
     Savaşı
    0.56
    POSITIVE LOGITS
     social
    0.62
     soon
    0.61
     thorough
    0.60
    rough
    0.57
     (
    0.57
    AC
    0.57
     D
    0.56
     because
    0.56
     or
    0.56
     summar
    0.56
    Act Density 0.669%

    No Known Activations