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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron primarily responds to punctuation marks—especially period tokens that end sentences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    discussion
    -0.07
    λος
    -0.07
    lope
    -0.07
     ελλην
    -0.06
    Chart
    -0.06
    ('.')↵
    -0.06
     Âu
    -0.06
    ugal
    -0.06
    adb
    -0.06
    /tty
    -0.06
    POSITIVE LOGITS
    ش
    0.06
     FIFO
    0.06
     fenced
    0.06
     крем
    0.06
     miesz
    0.06
     DataType
    0.06
    ег
    0.06
     قتل
    0.06
     Ш
    0.06
     downstream
    0.05
    Act Density 0.001%

    No Known Activations