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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COVID
    -0.07
     methane
    -0.07
     gallery
    -0.06
     dialog
    -0.06
     Zoom
    -0.06
    SCO
    -0.06
     STEP
    -0.06
    slack
    -0.06
     Glass
    -0.06
     ende
    -0.06
    POSITIVE LOGITS
     casa
    0.08
    .fml
    0.07
     maison
    0.06
    吸
    0.06
    [OF
    0.06
     модели
    0.06
    ，看
    0.06
     karena
    0.06
    編
    0.06
    (Double
    0.05
    Act Density 0.000%

    No Known Activations