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

    Neuronpedia

    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CLR
    -0.07
    �藏
    -0.06
    bu
    -0.06
    acle
    -0.06
     Supports
    -0.06
     provides
    -0.06
    rails
    -0.06
     Zip
    -0.06
     ServiceProvider
    -0.06
     LANGUAGE
    -0.06
    POSITIVE LOGITS
     bumper
    0.07
    貼
    0.06
    .test
    0.06
    bow
    0.06
     Oprah
    0.06
    -em
    0.06
     finans
    0.06
    ovation
    0.06
    %m
    0.06
    &m
    0.06
    Act Density 0.024%

    No Known Activations