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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fracking
    -0.07
    <C
    -0.07
    weekday
    -0.07
     Hipp
    -0.06
     Haram
    -0.06
    κού
    -0.06
    اه
    -0.06
     POW
    -0.06
     knock
    -0.06
     Frag
    -0.06
    POSITIVE LOGITS
    化学
    0.07
     ""},↵
    0.06
     Nvidia
    0.06
     Mul
    0.06
    长度
    0.06
    ในร
    0.06
    、日本
    0.06
    emons
    0.06
    원을
    0.06
     输
    0.06
    Act Density 0.005%

    No Known Activations