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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing a decimal point (i.e. non‐integer numbers) in arithmetic problems.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    udge
    -0.06
    lech
    -0.06
     {$
    -0.06
    ché
    -0.06
     radi
    -0.06
     giy
    -0.06
     بت
    -0.06
    ,function
    -0.06
     retailers
    -0.06
     관리
    -0.06
    POSITIVE LOGITS
    NSAttributedString
    0.07
    едини
    0.07
     COURT
    0.06
     Мик
    0.06
     απο
    0.06
    iostream
    0.06
    رفته
    0.06
    ابع
    0.06
     dieses
    0.06
     Exc
    0.06
    Act Density 0.011%

    No Known Activations