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

    Neuronpedia

    INDEX
    Explanations

    confidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rollback
    -0.07
    guide
    -0.07
     UIResponder
    -0.06
    uppercase
    -0.06
    ذلك
    -0.06
     AssemblyCopyright
    -0.06
    Baseline
    -0.06
     showAlert
    -0.06
    보다
    -0.06
    (IO
    -0.06
    POSITIVE LOGITS
     evolution
    0.06
    ？
    0.06
    iedy
    0.06
     ****************
    0.06
     Plug
    0.06
    (animation
    0.06
     ดาว
    0.06
    CBS
    0.06
     citations
    0.06
     routines
    0.06
    Act Density 0.011%

    No Known Activations