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

    Neuronpedia

    INDEX
    Explanations

    IPython.display

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resentment
    -0.09
     expend
    -0.08
     pursuits
    -0.08
     motivations
    -0.08
    _UNKNOWN
    -0.08
     pursuit
    -0.08
    ði
    -0.08
     assumed
    -0.08
    cial
    -0.08
     deviation
    -0.08
    POSITIVE LOGITS
    .inline
    0.13
     hyperlink
    0.10
    .display
    0.09
     Sage
    0.09
     hyperlinks
    0.09
    aaring
    0.09
    ritter
    0.09
    _inline
    0.08
    .Display
    0.08
    äpp
    0.08
    Act Density 0.004%

    No Known Activations