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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    普惠
    -0.07
     undeniable
    -0.07
    賺
    -0.07
     dành
    -0.07
     ppm
    -0.07
     behavioral
    -0.06
     Derby
    -0.06
     Specialists
    -0.06
    isspace
    -0.06
     plastics
    -0.06
    POSITIVE LOGITS
    ˓
    0.07
    fila
    0.07
    ,long
    0.07
    contin
    0.07
    andoned
    0.07
    (COM
    0.06
    (styles
    0.06
    าง
    0.06
     Doesn
    0.06
    冻
    0.06
    Act Density 0.109%

    No Known Activations