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

    Neuronpedia

    INDEX
    Explanations

    TABLE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mint
    -0.07
    .conf
    -0.07
    素质
    -0.07
    .Con
    -0.07
    _ARCHIVE
    -0.06
     Falcons
    -0.06
    integration
    -0.06
    Intel
    -0.06
    今天的
    -0.06
     pk
    -0.06
    POSITIVE LOGITS
    uly
    0.07
    ock
    0.07
    //'
    0.07
    -popup
    0.07
     várias
    0.07
    풉
    0.06
     chez
    0.06
    _che
    0.06
    州区
    0.06
     unlawful
    0.06
    Act Density 0.002%

    No Known Activations