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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    the presence of floating-point numeric literals (decimal constants) in source code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     nên
    -0.06
     motifs
    -0.06
     checkout
    -0.06
    grese
    -0.06
     Networks
    -0.06
     flushed
    -0.06
     JSGlobal
    -0.06
     ='
    -0.06
    Granted
    -0.06
     openid
    -0.06
    POSITIVE LOGITS
    Alive
    0.07
    	reg
    0.07
    ोध
    0.06
    .Join
    0.06
     winding
    0.06
    lay
    0.06
     згад
    0.06
    _REQUIRE
    0.06
     raw
    0.06
    ,,
    0.06
    Act Density 0.019%

    No Known Activations