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

    Neuronpedia

    INDEX
    Explanations

    terms starting with pp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yardımcı
    0.44
    σε
    0.41
    мати
    0.39
     aspiring
    0.39
    puesta
    0.38
     cuốn
    0.38
     خارجی
    0.38
    ന്ദ
    0.38
     सार्वजनिक
    0.38
     бу
    0.37
    POSITIVE LOGITS
     PPI
    0.70
     PP
    0.68
    PP
    0.68
    PPP
    0.63
    PPI
    0.61
     PPP
    0.61
     PPR
    0.60
     pp
    0.59
     PPG
    0.56
     PPE
    0.55
    Act Density 0.008%

    No Known Activations