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

    Neuronpedia

    INDEX
    Explanations

    analytics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Impl
    -0.07
    krv
    -0.06
     Forever
    -0.06
     reset
    -0.06
     Sic
    -0.06
    .order
    -0.06
    /filter
    -0.06
     ymax
    -0.06
     Visible
    -0.06
    (screen
    -0.06
    POSITIVE LOGITS
    Problem
    0.07
     dean
    0.07
     conformity
    0.07
     Eğitim
    0.07
     Teens
    0.07
     teal
    0.07
     jour
    0.07
    InputDialog
    0.06
    Are
    0.06
    ":[{"
    0.06
    Act Density 0.029%

    No Known Activations