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

    Neuronpedia

    INDEX
    Explanations

    gradual changes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iveness
    -0.08
     fft
    -0.07
    ()↵↵
    -0.06
    Over
    -0.06
    heritance
    -0.06
    Bei
    -0.06
    115
    -0.06
    already
    -0.06
     Principles
    -0.06
     marriage
    -0.06
    POSITIVE LOGITS
     screw
    0.07
    ูป
    0.07
    ęd
    0.07
     melakukan
    0.07
    項
    0.06
     prevented
    0.06
     Steelers
    0.06
     drove
    0.06
     büny
    0.06
     resisted
    0.06
    Act Density 0.014%

    No Known Activations