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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amber
    -0.08
     victims
    -0.08
     KIND
    -0.07
    equipment
    -0.07
     illuminated
    -0.07
     integrity
    -0.07
     digit
    -0.07
    ázd
    -0.07
    Kr
    -0.07
    footer
    -0.07
    POSITIVE LOGITS
    APIView
    0.06
    /cpp
    0.06
     __("
    0.06
     مدينة
    0.06
     Laptop
    0.05
    什么
    0.05
    云
    0.05
    ีอย
    0.05
    -chain
    0.05
    醫
    0.05
    Act Density 0.003%

    No Known Activations