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

    Neuronpedia

    INDEX
    Explanations

    ual

    np_max-act · gemini-2.0-flash

    reference to medical research or clinical studies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The main thing this neuron does is detect specialized, domain-specific jargon or uncommon technical terms across scientific, medical, and programming contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    yield
    -0.07
    departure
    -0.07
     xmlDoc
    -0.07
    RETURN
    -0.06
    FileSize
    -0.06
    keydown
    -0.06
     getLogger
    -0.06
    .Here
    -0.06
     Collapse
    -0.06
     vardır
    -0.06
    POSITIVE LOGITS
     universally
    0.07
    .s
    0.07
     social
    0.06
    -wise
    0.06
     laws
    0.06
    一般
    0.06
    Pieces
    0.06
     global
    0.06
     inspires
    0.06
     commentators
    0.06
    Act Density 0.000%

    No Known Activations