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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron fires on C++ code tokens—especially library function/algorithm names, type names, and identifiers—distinguishing code elements from plain text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    urtles
    -0.08
    LogLevel
    -0.07
    _review
    -0.07
    datagrid
    -0.07
     Enter
    -0.06
     Earth
    -0.06
    %%↵
    -0.06
    pdf
    -0.06
    Icon
    -0.06
    	CString
    -0.06
    POSITIVE LOGITS
    郎
    0.07
    ovala
    0.07
     مورد
    0.07
    isos
    0.06
    _increase
    0.06
     siyasi
    0.06
     Tomas
    0.06
     Nej
    0.06
     continuing
    0.06
     чай
    0.06
    Act Density 0.049%

    No Known Activations