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

    Neuronpedia

    INDEX
    Explanations

    Sports game summaries

    np_max-act · gemini-2.0-flash

    The neuron primarily detects structural breaks in the text—i.e. paragraph or sentence boundaries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Prot
    -0.07
     pipeline
    -0.07
    ”:
    -0.07
    디
    -0.07
    TER
    -0.06
     før
    -0.06
     Wants
    -0.06
    ÓN
    -0.06
    ypes
    -0.06
     Blind
    -0.06
    POSITIVE LOGITS
    ेप
    0.07
    هد
    0.07
     passion
    0.06
    سل
    0.06
    บาท
    0.06
    .IT
    0.06
    िजन
    0.06
    一人
    0.05
     Wald
    0.05
     дина
    0.05
    Act Density 0.014%

    No Known Activations