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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    두
    -0.07
     خانواده
    -0.06
     못
    -0.06
     Algorithm
    -0.06
    oscopic
    -0.06
     Thương
    -0.06
    Class
    -0.06
    mise
    -0.06
    Keyboard
    -0.06
     soils
    -0.06
    POSITIVE LOGITS
     Fees
    0.07
     refund
    0.07
    =models
    0.07
     inner
    0.06
    maya
    0.06
    volt
    0.06
    อค
    0.06
    imax
    0.06
     incentiv
    0.06
    _mail
    0.06
    Act Density 0.010%

    No Known Activations