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

    Neuronpedia

    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash

    This neuron activates on directory or module names in C/C++ #include paths (e.g. “base,” “content,” “components,” “third_party,” “net,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     perfected
    -0.07
    ////////////////////////////////////////////////////////////////////////
    -0.07
    كار
    -0.07
    -----------↵↵
    -0.07
     presentations
    -0.06
     Kom
    -0.06
    (defun
    -0.06
    ++;↵
    -0.06
    _PERIOD
    -0.06
    setter
    -0.06
    POSITIVE LOGITS
    роб
    0.06
     previously
    0.06
    _address
    0.06
    postData
    0.06
    hall
    0.06
    abby
    0.06
    Orth
    0.06
    ')";↵
    0.06
    ylv
    0.06
    ционных
    0.06
    Act Density 0.002%

    No Known Activations