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

    Neuronpedia

    INDEX
    Explanations

    assignment and initialization syntax in programming code

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

    protobuf definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.51
    Nationalité
    -0.48
     disponibilités
    -0.48
     aprendido
    -0.48
     escuchado
    -0.42
     normaux
    -0.41
     absorción
    -0.41
     thermique
    -0.41
     transferencia
    -0.40
     ainfi
    -0.40
    POSITIVE LOGITS
     separate
    0.46
     official
    0.45
     def
    0.45
    ┓
    0.45
     detailed
    0.45
    basicConfig
    0.45
     proof
    0.44
     step
    0.43
     thoroughly
    0.43
     farm
    0.43
    Act Density 0.011%

    No Known Activations