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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash

    This neuron detects when a term or keyword is presented in quotation marks, as in definitions or discussions of specific words.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     lost
    -0.07
    τς
    -0.07
    ;k
    -0.06
    783
    -0.06
    .Commit
    -0.06
    )):↵
    -0.06
    resents
    -0.06
     숨
    -0.06
     pas
    -0.06
    Aws
    -0.06
    POSITIVE LOGITS
     usize
    0.07
     Or
    0.07
    Quarter
    0.06
     lipid
    0.06
     aynı
    0.06
    _fname
    0.06
     پیامبر
    0.06
    (Member
    0.06
    [label
    0.06
     ElementType
    0.06
    Act Density 0.022%

    No Known Activations