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

    Neuronpedia

    INDEX
    Explanations

    thanks, welcome

    np_max-act · gemini-2.0-flash

    The neuron fires on the interviewer's opening pleasantries and greetings—i.e. the “Hi there, thanks for joining us today”–style introductory lines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     филь
    -0.06
     ("<
    -0.06
     DEFIN
    -0.06
     sculpt
    -0.06
    _written
    -0.06
    _cov
    -0.06
    :frame
    -0.06
    这些
    -0.06
    _pol
    -0.06
     judges
    -0.06
    POSITIVE LOGITS
     fık
    0.08
     civilians
    0.07
    Tk
    0.07
    ,-
    0.07
    0.07
    igrated
    0.06
     sexist
    0.06
     ################################################
    0.06
     ine
    0.06
    +"<
    0.06
    Act Density 0.023%

    No Known Activations