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

    Neuronpedia

    INDEX
    Explanations

    concepts related to emotional intelligence and personal awareness

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

    definitions, categories, abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⟬
    -0.66
    <unused79>
    -0.65
    [@BOS@]
    -0.65
    <pad>
    -0.65
    <unused16>
    -0.65
    <unused23>
    -0.65
    <unused41>
    -0.65
    <unused52>
    -0.65
    <unused42>
    -0.65
    <unused3>
    -0.65
    POSITIVE LOGITS
     êtres
    0.37
     Formación
    0.34
     vérit
    0.29
     Trouvez
    0.28
     prêtres
    0.28
     dieux
    0.28
     actuels
    0.28
     normaux
    0.27
    geführt
    0.26
     boneca
    0.26
    Act Density 0.073%

    No Known Activations