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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and assertions in code

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

    Mathematical or logical expressions

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itinéraire
    -0.62
     pinulongan
    -0.60
    はじめに
    -0.60
     Мексичка
    -0.59
     Exacts
    -0.58
    Tembelea
    -0.55
    ESOME
    -0.54
     utafitiHapana
    -0.54
    AsUp
    -0.53
    FormTagHelper
    -0.53
    POSITIVE LOGITS
     maupun
    0.78
     illetve
    0.78
     or
    0.76
     valamint
    0.73
     and
    0.69
     وتسجيلات
    0.64
     että
    0.63
     lẫn
    0.56
     وكذلك
    0.55
     vs
    0.54
    Act Density 0.598%

    No Known Activations