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

    Neuronpedia

    INDEX
    Explanations

    punctuation and "and"

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal-point numbers (floating-point numeric values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rotor
    -0.07
    -road
    -0.07
     ترتیب
    -0.07
    统
    -0.07
    [n
    -0.06
    URING
    -0.06
     amusement
    -0.06
     Associated
    -0.06
    (pdev
    -0.06
     méně
    -0.06
    POSITIVE LOGITS
    ,it
    0.06
     Reverse
    0.06
     keen
    0.06
    ـ
    0.06
     neglect
    0.05
     Exact
    0.05
     Я
    0.05
    .posts
    0.05
    	describe
    0.05
    τε
    0.05
    Act Density 0.139%

    No Known Activations