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

    Neuronpedia

    INDEX
    Explanations

    Men

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hesitation
    -0.07
     promotions
    -0.06
     Processor
    -0.06
     Restaurant
    -0.06
     Exterior
    -0.06
    =d
    -0.06
     Christoph
    -0.06
     Babies
    -0.06
    (original
    -0.06
    06
    -0.06
    POSITIVE LOGITS
     men
    0.09
    /use
    0.08
     szer
    0.08
    men
    0.07
    Men
    0.07
     menn
    0.07
    alom
    0.07
     MEN
    0.07
     Men
    0.07
    ุษ
    0.07
    Act Density 0.023%

    No Known Activations