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

    Neuronpedia

    INDEX
    Explanations

    Taxonomy

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric year tokens (dates) that appear in taxonomic authority citations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    URRENT
    -0.07
    vre
    -0.06
    position
    -0.06
    Visual
    -0.06
    KeyEvent
    -0.06
    orrow
    -0.06
    .ToShort
    -0.06
    vc
    -0.06
    gh
    -0.06
    Battle
    -0.06
    POSITIVE LOGITS
    mean
    0.07
    (ins
    0.07
    _articles
    0.07
     відріз
    0.06
    ケース
    0.06
    可以
    0.06
     事
    0.06
    [dim
    0.06
     бі
    0.06
     Npgsql
    0.06
    Act Density 0.002%

    No Known Activations