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

    Neuronpedia

    INDEX
    Explanations

    character encoding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    変
    -0.07
    對
    -0.07
    Hop
    -0.07
    -Free
    -0.06
     icy
    -0.06
     페이지
    -0.06
    _CL
    -0.06
    .auto
    -0.06
    ρίου
    -0.06
     yere
    -0.06
    POSITIVE LOGITS
    }|
    0.07
     departing
    0.07
    289
    0.06
    ","
    0.06
     tasarım
    0.06
    ()));↵
    0.06
    Uh
    0.06
    0.06
    )),↵
    0.06
    Filed
    0.06
    Act Density 0.011%

    No Known Activations