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

    Neuronpedia

    INDEX
    Explanations

    Code syntax/delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Period
    -0.08
     alphanumeric
    -0.07
     random
    -0.07
    lish
    -0.07
    paging
    -0.07
    Copy
    -0.07
     cancers
    -0.07
    莱
    -0.06
     cancer
    -0.06
    Это
    -0.06
    POSITIVE LOGITS
     silah
    0.06
    _env
    0.06
    _ij
    0.06
     frente
    0.06
     Downs
    0.06
     dumpsters
    0.06
     OSD
    0.06
     sangat
    0.06
     tits
    0.06
    ọ
    0.06
    Act Density 0.005%

    No Known Activations