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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash

    The neuron activates on the directive “only,” i.e. tokens specifying an exclusivity constraint in instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     deaths
    -0.06
    цип
    -0.06
     placement
    -0.06
    .regex
    -0.06
     impair
    -0.06
    measure
    -0.06
     database
    -0.06
     measurable
    -0.06
     Message
    -0.06
     lore
    -0.06
    POSITIVE LOGITS
    capital
    0.07
     starší
    0.07
    _qp
    0.07
    آخر
    0.07
     typeid
    0.06
     выб
    0.06
     её
    0.06
     Demir
    0.06
     Capital
    0.06
     corporations
    0.06
    Act Density 0.015%

    No Known Activations