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

    Neuronpedia

    INDEX
    Explanations

    decisions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olis
    -0.08
    atches
    -0.07
    .getLogger
    -0.07
    ="${
    -0.07
     섬
    -0.07
    gif
    -0.06
    lez
    -0.06
    etric
    -0.06
    ken
    -0.06
    Before
    -0.06
    POSITIVE LOGITS
     Dorm
    0.07
     conserv
    0.06
     Forecast
    0.06
     Flyers
    0.06
    roveň
    0.06
    stdbool
    0.06
     Avalanche
    0.06
     Portable
    0.06
     Gry
    0.06
    vue
    0.06
    Act Density 0.019%

    No Known Activations