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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting in‐text numerical measurements, especially floating‐point numbers and related numeric values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    орт
    -0.07
    friendly
    -0.07
    문을
    -0.07
     measurement
    -0.07
     View
    -0.06
     contacts
    -0.06
    AQ
    -0.06
     Contacts
    -0.06
     qualche
    -0.06
     Pal
    -0.06
    POSITIVE LOGITS
    .isChecked
    0.06
    ((
    0.06
    uitable
    0.06
    	opts
    0.06
    ";↵↵
    0.06
    /ip
    0.06
     Hoe
    0.06
    .sendRedirect
    0.06
    .WriteHeader
    0.06
    íd
    0.06
    Act Density 0.027%

    No Known Activations