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

    Neuronpedia

    INDEX
    Explanations

    Major

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the standalone word “major” (in any capitalization) appears, especially as a heading or key descriptor.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ินท
    -0.07
    nowledge
    -0.06
    weet
    -0.06
     بتن
    -0.06
     уп
    -0.06
    BED
    -0.06
    ñas
    -0.06
     seedu
    -0.06
    уются
    -0.06
    ETweet
    -0.06
    POSITIVE LOGITS
     major
    0.15
     Major
    0.13
    Major
    0.11
    major
    0.10
     majors
    0.09
     Maj
    0.09
     jur
    0.08
    MR
    0.08
     AJ
    0.08
     RR
    0.08
    Act Density 0.018%

    No Known Activations