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

    Neuronpedia

    INDEX
    Explanations

    attr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ORIZED
    -0.07
    @Configuration
    -0.07
    蛔
    -0.07
    Ben
    -0.07
    有机
    -0.07
    �
    -0.07
    Legendary
    -0.07
     PU
    -0.07
    BILL
    -0.07
     perv
    -0.06
    POSITIVE LOGITS
     Fran
    0.07
    �
    0.07
    ं
    0.07
    Textbox
    0.07
    مس
    0.07
     dots
    0.07
    实战
    0.06
     Advisor
    0.06
    ₣
    0.06
    .scalajs
    0.06
    Act Density 0.001%

    No Known Activations