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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -</
    -0.08
     pictures
    -0.06
    -links
    -0.06
     enormous
    -0.06
    enské
    -0.06
    licant
    -0.06
     Falls
    -0.06
     realmente
    -0.06
     Address
    -0.06
     graduation
    -0.06
    POSITIVE LOGITS
    杜
    0.07
     �
    0.07
    เย
    0.06
    _Off
    0.06
     addObserver
    0.06
     Berk
    0.06
     reckon
    0.06
    arter
    0.06
    沖
    0.06
    �
    0.06
    Act Density 0.059%

    No Known Activations