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

    Neuronpedia

    INDEX
    Explanations

    programming constructs related to defining ranges or loops

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.33
     directed
    -0.32
     enough
    -0.32
     the
    -0.30
     teaching
    -0.30
     wait
    -0.29
     
    -0.29
     never
    -0.28
    ac
    -0.26
     should
    -0.26
    POSITIVE LOGITS
     Taktlose
    0.92
     Савезне
    0.90
     Autorizaciones
    0.90
     Biôgrafia
    0.83
     OFDb
    0.82
    ⟬
    0.82
    parsedMessage
    0.81
    oredCriteria
    0.81
     ProtoMessage
    0.80
    ViewImports
    0.79
    Act Density 0.002%

    No Known Activations