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

    Neuronpedia

    INDEX
    Explanations

    obligation

    np_max-act · gemini-2.0-flash

    This neuron activates on modal or normative verbs expressing what ought to or should happen (e.g. should, ought).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    enville
    -0.07
     tau
    -0.07
     included
    -0.07
     上海
    -0.06
    interpreted
    -0.06
     Пло
    -0.06
    وف
    -0.06
     Ih
    -0.06
    чень
    -0.06
    harga
    -0.06
    POSITIVE LOGITS
    �
    0.07
     раб
    0.07
     پیر
    0.06
     제가
    0.06
     Εκ
    0.06
    Ag
    0.06
     movement
    0.06
     milestones
    0.06
    $user
    0.06
    面
    0.06
    Act Density 0.096%

    No Known Activations