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

    Neuronpedia

    INDEX
    Explanations

    travel destinations/routes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    供需
    -0.08
    思想政治
    -0.07
    .XtraBars
    -0.07
    STOP
    -0.07
     Bison
    -0.06
    (@(
    -0.06
    _CMD
    -0.06
    itta
    -0.06
     Serena
    -0.06
    馬
    -0.06
    POSITIVE LOGITS
     Liquid
    0.08
    tório
    0.07
    -document
    0.07
    amento
    0.07
     resets
    0.07
     é
    0.07
     ];
↵
    0.07
     stale
    0.07
    ificação
    0.06
    します
    0.06
    Act Density 0.057%

    No Known Activations