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

    Neuronpedia

    INDEX
    Explanations

    Technical/Scientific context

    np_max-act · gemini-2.0-flash

    This neuron activates on verbs that describe cleaning and preparing items, as in cooking or food-preparation steps.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     پی
    -0.07
     패
    -0.06
    _ARCH
    -0.06
    퇴
    -0.06
    .amount
    -0.06
    อาร
    -0.06
     plagued
    -0.06
     hồ
    -0.06
    透
    -0.06
     hòa
    -0.06
    POSITIVE LOGITS
    .setObjectName
    0.07
    专业
    0.06
     غذ
    0.06
     muối
    0.06
    eden
    0.06
    ард
    0.06
     söy
    0.06
    onen
    0.06
    ,email
    0.06
     legit
    0.06
    Act Density 0.314%

    No Known Activations