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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Con
    -0.08
    _In
    -0.08
    فن
    -0.07
    ,in
    -0.07
    .con
    -0.07
     Size
    -0.07
    enn
    -0.07
    Rec
    -0.07
    인가
    -0.06
    σεων
    -0.06
    POSITIVE LOGITS
     Y
    0.06
     Этот
    0.06
    -marker
    0.06
     buy
    0.06
    Propagation
    0.06
    Spot
    0.06
     pornstar
    0.06
     bought
    0.06
     coder
    0.05
     możli
    0.05
    Act Density 0.034%

    No Known Activations