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

    Neuronpedia

    INDEX
    Explanations

    drawing attention, recounting events

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on first‐person references (e.g. “I,” “others”) and the immediate action or reaction verbs that follow them.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     جدید
    -0.07
    lord
    -0.07
    EA
    -0.07
    iqué
    -0.06
     capsule
    -0.06
    .WRAP
    -0.06
    ату
    -0.06
    ILITIES
    -0.06
    empre
    -0.06
    ると
    -0.06
    POSITIVE LOGITS
     dhe
    0.07
    _schedule
    0.06
     podařilo
    0.06
     getDefault
    0.06
     Abstract
    0.06
     companyId
    0.06
    (attribute
    0.06
     relying
    0.06
     clam
    0.06
     располаг
    0.06
    Act Density 0.166%

    No Known Activations