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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash

    The neuron responds to communication verbs indicating that one party informs or tells another something.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ｡
    -0.07
     candid
    -0.07
     peas
    -0.06
     dau
    -0.06
    เอง
    -0.06
     affected
    -0.06
     Urs
    -0.06
    .FixedSingle
    -0.06
    pha
    -0.06
    _sku
    -0.06
    POSITIVE LOGITS
    ystick
    0.07
    	final
    0.07
    كال
    0.06
     restarting
    0.06
    <Vertex
    0.06
    .Drop
    0.06
    olve
    0.06
    ويس
    0.06
    λλη
    0.06
    eventName
    0.06
    Act Density 0.012%

    No Known Activations