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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash

    This neuron detects conditional constructions (e.g., “if…approved,” “Wenn…”) that introduce outcome clauses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iale
    -0.06
     backButton
    -0.06
     wisdom
    -0.06
     таком
    -0.06
    .rotation
    -0.06
     vznik
    -0.06
     lanes
    -0.06
    centers
    -0.06
    (board
    -0.06
     betrayed
    -0.06
    POSITIVE LOGITS
     зан
    0.07
     моб
    0.07
     ऊ
    0.07
     Supplementary
    0.07
     repost
    0.06
    acted
    0.06
    .Unicode
    0.06
     grub
    0.06
     تط
    0.06
    τός
    0.06
    Act Density 0.035%

    No Known Activations