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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sizer
    -0.08
     instinct
    -0.07
     dish
    -0.07
    strcmp
    -0.07
     impedance
    -0.07
     مجموع
    -0.07
    meter
    -0.07
    DEX
    -0.07
     interrom
    -0.07
     വിഭ
    -0.07
    POSITIVE LOGITS
     leather
    0.08
     Best
    0.08
     famous
    0.07
     ect
    0.07
     Fau
    0.07
     Critics
    0.07
     Leather
    0.07
     strongest
    0.07
     disproportionately
    0.07
     :'
    0.07
    Act Density 0.011%

    No Known Activations