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 activates on code identifiers ending in “Informer,” i.e. type or function names that include the suffix Informer.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SHIPPING
    -0.07
    	fs
    -0.07
    磁
    -0.06
     lesen
    -0.06
    ospace
    -0.06
    _curr
    -0.06
    ถ
    -0.06
     hoping
    -0.06
     regex
    -0.06
    automation
    -0.06
    POSITIVE LOGITS
     ddl
    0.08
    ीच
    0.06
    paren
    0.06
     를
    0.06
    (spell
    0.06
     Claudia
    0.06
     Football
    0.06
     buffalo
    0.06
    ظٹط
    0.06
    ?>">
↵
    0.06
    Act Density 0.046%

    No Known Activations