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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash

    The neuron is primarily detecting the isolated token “g.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Vale
    -0.07
    eken
    -0.06
    acent
    -0.06
     програ
    -0.06
     VARCHAR
    -0.06
     McDonald
    -0.06
    Tahoma
    -0.06
     nejd
    -0.06
     Fitzgerald
    -0.06
    _Insert
    -0.06
    POSITIVE LOGITS
    ducer
    0.07
    security
    0.07
    ductor
    0.07
    thern
    0.07
    Employ
    0.07
     gossip
    0.06
    -depend
    0.06
    pets
    0.06
    ickname
    0.06
     SY
    0.06
    Act Density 0.001%

    No Known Activations