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

    Neuronpedia

    INDEX
    Explanations

    wild

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Evan
    -0.08
     Vi
    -0.08
     tagline
    -0.08
     বিষয়
    -0.07
     Elvis
    -0.07
    VIII
    -0.07
    -0.07
     Winn
    -0.07
     platter
    -0.07
    svc
    -0.07
    POSITIVE LOGITS
     untouched
    0.10
    自然
    0.09
     naturels
    0.09
     doğal
    0.09
     प्राकृतिक
    0.09
     intact
    0.09
     طبیعی
    0.09
     luonn
    0.09
     natürlichen
    0.08
     alami
    0.08
    Act Density 0.021%
    No Known Activations