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

    Neuronpedia

    INDEX
    Explanations

    period character

    np_max-act · gemini-2.0-flash

    The neuron detects individual period “.” punctuation tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    aires
    -0.07
    ́
    -0.07
     Undefined
    -0.06
    .On
    -0.06
     Button
    -0.06
    joining
    -0.06
    ίσω
    -0.06
     tactical
    -0.06
     biến
    -0.06
     "";
    -0.06
    POSITIVE LOGITS
     MÜ
    0.07
     Wikip
    0.06
     miscon
    0.06
    ครบ
    0.06
    .MODEL
    0.06
     khẳng
    0.06
    ापक
    0.06
    Tro
    0.06
    	priv
    0.06
    breaking
    0.06
    Act Density 0.658%

    No Known Activations