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

    Neuronpedia

    INDEX
    Explanations

    mostly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lite
    -0.07
     precarious
    -0.07
    έργ
    -0.06
     σαν
    -0.06
     urgent
    -0.06
     bio
    -0.06
     errmsg
    -0.06
     kwargs
    -0.06
    啊啊
    -0.06
    ường
    -0.06
    POSITIVE LOGITS
     mostly
    0.12
    mostly
    0.07
     Cory
    0.07
    �
    0.07
     Mostly
    0.06
     most
    0.06
     Corey
    0.06
     Carroll
    0.06
    .lesson
    0.06
     socks
    0.06
    Act Density 0.005%

    No Known Activations