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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    species of moths and their classifications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on the word “described” in category lines (e.g. “Moths described in YYYY”) indicating when a species was formally described.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    WEST
    -0.07
    _fw
    -0.06
    odes
    -0.06
    Wonder
    -0.06
    рам
    -0.06
    _uploaded
    -0.06
     embargo
    -0.06
    jee
    -0.06
    SF
    -0.06
    evším
    -0.06
    POSITIVE LOGITS
     tonumber
    0.07
     Banking
    0.06
    通り
    0.06
    Lock
    0.06
     تعداد
    0.06
    Council
    0.06
     resolving
    0.06
    リンク
    0.06
     squares
    0.06
     informed
    0.06
    Act Density 0.001%

    No Known Activations