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

    Neuronpedia

    INDEX
    Explanations

    Spare parts or items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haine
    -0.09
     syrup
    -0.08
     amateur
    -0.08
     bible
    -0.08
     Dam
    -0.08
     foreclosure
    -0.07
     Saf
    -0.07
     Maze
    -0.07
     Haag
    -0.07
     saf
    -0.07
    POSITIVE LOGITS
    aneously
    0.09
     kus
    0.08
    819
    0.08
     마련
    0.08
    帯
    0.07
    want
    0.07
    aneous
    0.07
     linewidth
    0.07
    253
    0.07
    Luke
    0.07
    Act Density 0.089%

    No Known Activations