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

    Neuronpedia

    INDEX
    Explanations

    timing of events

    np_max-act · gemini-2.0-flash

    The neuron chiefly detects negative or contrastive markers (e.g. “not,” “did,” “though,” “become” in negating contexts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _EXISTS
    -0.07
    ール
    -0.06
    ocode
    -0.06
     ---------------------------------------------------------------------------↵
    -0.06
    oftware
    -0.06
    سته
    -0.06
    �
    -0.06
    켓
    -0.06
     polít
    -0.06
    ymi
    -0.06
    POSITIVE LOGITS
    (-
    0.07
     outsider
    0.06
     electrons
    0.06
    VOID
    0.06
     Jest
    0.06
    (icon
    0.06
    /task
    0.06
    +/
    0.06
     barcelona
    0.06
    (=
    0.06
    Act Density 0.070%

    No Known Activations