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

    Neuronpedia

    INDEX
    Explanations

    sequence

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on the token “sequence” (as used in the repeated “probability of sequence …” phrases).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tn
    -0.07
    parentNode
    -0.07
     wildly
    -0.06
     ActiveRecord
    -0.06
    托
    -0.06
    ูก
    -0.06
    LOSS
    -0.06
     tokenize
    -0.06
    оты
    -0.06
     onions
    -0.06
    POSITIVE LOGITS
    -General
    0.07
     Action
    0.07
    feit
    0.07
     dtype
    0.06
    .makedirs
    0.06
    _context
    0.06
    šem
    0.06
    Health
    0.06
    .netty
    0.06
    시에
    0.06
    Act Density 0.001%

    No Known Activations