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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the phrase “covered by” (often “covered by the”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    '
↵
    -0.07
    ()
↵
↵
↵
    -0.07
    __':
↵
    -0.07
    えた
    -0.07
     Collins
    -0.06
     Out
    -0.06
    ΟΤ
    -0.06
     인터
    -0.06
    ={`/
    -0.06
    اوه
    -0.06
    POSITIVE LOGITS
     administr
    0.07
     jouer
    0.06
     encompasses
    0.06
     BaseModel
    0.06
    @FXML
    0.06
     prev
    0.06
    つぶ
    0.05
     المللی
    0.05
     McMaster
    0.05
    @register
    0.05
    Act Density 0.011%

    No Known Activations