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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects the discourse marker “Again,” when a response repeats or reinforces a point.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Delayed
    -0.07
     Parsons
    -0.06
    Roboto
    -0.06
     감사
    -0.06
    áng
    -0.06
     postponed
    -0.06
    issuer
    -0.06
     Emblem
    -0.06
    OUR
    -0.06
    캐
    -0.06
    POSITIVE LOGITS
    _model
    0.07
    rotation
    0.07
     influences
    0.07
    .datasets
    0.07
    (cursor
    0.06
    固定
    0.06
    _SLAVE
    0.06
    materials
    0.06
    寒
    0.06
     grotes
    0.06
    Act Density 0.013%

    No Known Activations