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

    Neuronpedia

    INDEX
    Explanations

    "

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /j
    -0.07
     /=
    -0.07
    ․
    -0.06
    🕖
    -0.06
    ﺏ
    -0.06
    FTP
    -0.06
    🐌
    -0.06
     сайте
    -0.06
     chancellor
    -0.06
    /ex
    -0.06
    POSITIVE LOGITS
     Mostly
    0.07
    .Repositories
    0.07
     Param
    0.07
     instincts
    0.07
    最受
    0.07
    ](↵
    0.07
    jang
    0.07
     physiological
    0.07
    Profit
    0.07
    inqu
    0.07
    Act Density 0.003%

    No Known Activations