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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of multi‐function or multifunction tools/devices—that is, words signaling “multi-function” functionality.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _direct
    -0.06
     ngon
    -0.06
     ESC
    -0.06
    persistent
    -0.06
    720
    -0.06
    สต
    -0.06
     IEnumerable
    -0.05
     अग
    -0.05
     censorship
    -0.05
     pisc
    -0.05
    POSITIVE LOGITS
    バス
    0.08
    Strategy
    0.07
     Martial
    0.07
    dress
    0.07
    Tumblr
    0.07
    seeing
    0.07
    -purpose
    0.07
     Oasis
    0.07
     martial
    0.06
     lieu
    0.06
    Act Density 0.015%

    No Known Activations