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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    葫
    -0.07
     lyn
    -0.07
    纪检
    -0.07
    html
    -0.07
    劳动合同
    -0.07
    .ascii
    -0.07
     prophets
    -0.07
    ammad
    -0.07
    ﮈ
    -0.07
    Leon
    -0.07
    POSITIVE LOGITS
    PackageName
    0.07
     historia
    0.07
    зал
    0.07
    됏
    0.07
     complicated
    0.06
     Scenario
    0.06
    Separator
    0.06
     strength
    0.06
     concluded
    0.06
     called
    0.06
    Act Density 0.002%

    No Known Activations