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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frauen
    -0.06
    рит
    -0.06
     irq
    -0.06
     kinh
    -0.06
     souhlas
    -0.06
    >--}}↵
    -0.06
    _numer
    -0.06
    ($('#
    -0.06
    费用
    -0.06
     групп
    -0.06
    POSITIVE LOGITS
                
    0.07
    emaker
    0.07
     feasibility
    0.07
     prosecutions
    0.06
     transparency
    0.06
     Enforcement
    0.06
    _Exception
    0.06
    CDF
    0.06
     blending
    0.06
    designation
    0.06
    Act Density 0.023%

    No Known Activations