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

    Neuronpedia

    INDEX
    Explanations

    User-generated content

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to sentence-ending punctuation (periods, exclamation points, question marks) that mark sentence boundaries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     snippet
    -0.06
    該
    -0.06
    -add
    -0.06
     Agree
    -0.06
    ukes
    -0.06
    ierten
    -0.06
    ины
    -0.06
    ierte
    -0.06
    medium
    -0.06
    ाहन
    -0.06
    POSITIVE LOGITS
    $core
    0.07
    обра�
    0.06
    (newState
    0.06
     hexatrigesimal
    0.06
    eyin
    0.06
     nood
    0.06
     localVar
    0.06
     tvb
    0.06
     dospěl
    0.06
    mayın
    0.06
    Act Density 0.022%

    No Known Activations