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

    Neuronpedia

    INDEX
    Explanations

    JSON objects and their structures

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

    code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obligé
    -0.35
     asesinado
    -0.33
     asimismo
    -0.30
     mejorado
    -0.30
     empleos
    -0.30
     saludos
    -0.30
    AnimationsModule
    -0.29
     troca
    -0.28
     perhaps
    -0.28
     quizá
    -0.28
    POSITIVE LOGITS
    <unused74>
    0.81
    <unused23>
    0.81
    <pad>
    0.81
    [@BOS@]
    0.81
    <unused51>
    0.81
    <unused14>
    0.81
    <unused43>
    0.81
    <unused16>
    0.81
    <unused3>
    0.81
    <unused8>
    0.81
    Act Density 0.027%

    No Known Activations