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

    Neuronpedia

    INDEX
    Explanations

    translation

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of matrix transformation operations—especially the names “Translate,” “Rotation,” and “Scale.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ()(
    -0.07
    ワー
    -0.07
    BYTES
    -0.06
    Attempting
    -0.06
    run
    -0.06
    	dto
    -0.06
    紧
    -0.06
    loyment
    -0.06
    akedirs
    -0.06
    dup
    -0.06
    POSITIVE LOGITS
     trình
    0.07
     vyd
    0.07
     accents
    0.06
    s
    0.06
     ModelState
    0.06
     transl
    0.06
     Study
    0.06
     dịch
    0.06
     porcelain
    0.06
    ionario
    0.06
    Act Density 0.004%

    No Known Activations