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

    Neuronpedia

    INDEX
    Explanations

    belong

    np_max-act · gemini-2.0-flash

    The neuron is detecting instances of the verb “belong” (and its inflected forms like “belongs”), i.e. expressions of possession or membership.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     onCreateView
    -0.07
    �
    -0.07
    試
    -0.07
    訓
    -0.07
    .im
    -0.07
    -т
    -0.06
    rowser
    -0.06
    偷
    -0.06
     Kiểm
    -0.06
    617
    -0.06
    POSITIVE LOGITS
     belong
    0.13
     belongs
    0.13
     belonged
    0.12
     belonging
    0.12
    belongsTo
    0.08
     pertaining
    0.08
     belongings
    0.07
     correspond
    0.07
    endon
    0.07
     importing
    0.07
    Act Density 0.007%

    No Known Activations