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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cao
    -0.07
     شو
    -0.07
    /movie
    -0.06
     WWW
    -0.06
    نس
    -0.06
    اوت
    -0.06
     Convert
    -0.06
    TEMPL
    -0.06
    ERIC
    -0.06
    سوب
    -0.06
    POSITIVE LOGITS
     irres
    0.07
    "k
    0.07
    hardware
    0.06
    所属
    0.06
     delim
    0.06
    -created
    0.06
     )"
    0.06
    phylum
    0.06
    issing
    0.06
    lası
    0.06
    Act Density 0.071%

    No Known Activations