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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of files—especially code tokens referring to opening, reading, or otherwise manipulating a file path.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ponent
    -0.07
     breaches
    -0.07
     Armenia
    -0.06
    typeorm
    -0.06
    敌
    -0.06
    -floor
    -0.06
     Higgins
    -0.06
     Kunden
    -0.06
    کنان
    -0.06
    KW
    -0.06
    POSITIVE LOGITS
     行
    0.06
    .integer
    0.06
    oops
    0.06
    เมตร
    0.06
     :.:
    0.06
    isl
    0.06
     vytvoř
    0.06
     Eag
    0.06
    AlgorithmException
    0.06
    ,E
    0.06
    Act Density 0.012%

    No Known Activations