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

    Neuronpedia

    INDEX
    Explanations

    gig work and odd jobs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Enjoy
    0.41
    專
    0.40
    руп
    0.40
     Ruhe
    0.40
    <0x8F>
    0.39
     chuyên
    0.39
     متخصص
    0.39
     Enjoy
    0.38
     Tark
    0.38
     sağlıklı
    0.38
    POSITIVE LOGITS
     gig
    1.10
     odd
    1.02
     gigs
    1.01
     Gig
    0.93
    Odd
    0.93
    Gig
    0.91
    odd
    0.86
    gig
    0.85
     Odd
    0.83
     babys
    0.80
    Act Density 0.022%

    No Known Activations