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

    Neuronpedia

    INDEX
    Explanations

    Definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    car
    -0.88
     scene
    -0.73
     car
    -0.69
    AnchorStyles
    -0.65
     EconPapers
    -0.65
    PrototypeOf
    -0.57
     her
    -0.56
    scene
    -0.56
     mug
    -0.54
     Car
    -0.53
    POSITIVE LOGITS
     démocr
    0.79
    hips
    0.71
     digitais
    0.61
     judicia
    0.59
     auffi
    0.58
     LIRE
    0.58
    itaires
    0.57
     ainfi
    0.57
    zbęd
    0.57
     électriques
    0.56
    Act Density 0.104%

    No Known Activations