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
    Printer
    -0.06
    Parser
    -0.06
    (parser
    -0.06
    ＋
    -0.06
    362
    -0.06
    358
    -0.06
     "";
    -0.06
     suyu
    -0.06
     borderColor
    -0.06
    ческих
    -0.06
    POSITIVE LOGITS
    (Roles
    0.07
     demol
    0.07
    创
    0.07
    elli
    0.06
    MouseClicked
    0.06
     finanzi
    0.06
    emotion
    0.06
     outliers
    0.06
     منزل
    0.06
     цент
    0.06
    Act Density 0.002%

    No Known Activations