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

    Neuronpedia

    INDEX
    Explanations

    burn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abox
    -0.27
    å´İ
    -0.25
    ugo
    -0.25
    éķ¿è¿ľ
    -0.24
    odon
    -0.24
    ician
    -0.24
    reet
    -0.24
    wagon
    -0.24
    riers
    -0.24
    alon
    -0.23
    POSITIVE LOGITS
     scheme
    0.29
     sort
    0.27
     Brexit
    0.27
    æĪĽ
    0.25
     Clarkson
    0.25
     Scheme
    0.25
    çļĦç«ŀäºī
    0.24
    -tm
    0.24
     humanity
    0.24
     for
    0.24
    Act Density 0.071%

    No Known Activations