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

    Neuronpedia

    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting the phrase “method of” (i.e. occurrences of “method” immediately followed by “of”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    аков
    -0.07
    riends
    -0.06
    urate
    -0.06
     composers
    -0.06
    anship
    -0.06
     ウ
    -0.06
    ecess
    -0.06
    olf
    -0.06
    eno
    -0.05
    .iv
    -0.05
    POSITIVE LOGITS
    SetTitle
    0.07
     '';↵
    0.07
    rsa
    0.07
     ')
↵
    0.07
     تنظيف
    0.06
     Закону
    0.06
    navigate
    0.06
     exemptions
    0.06
     :↵
    0.06
    (
↵
    0.06
    Act Density 0.006%

    No Known Activations