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

    Neuronpedia

    INDEX
    Explanations

    references to emotional or psychological distress

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

    Follows "removed", "an", or "(" tokens

    np_acts-logits-general · gemini-2.0-flash

    removed his, an upper, activity during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.62
     beginnetje
    -0.56
    WriteTagHelper
    -0.51
     myſelf
    -0.48
    parsedMessage
    -0.48
     Rtl
    -0.47
    saraba
    -0.46
    ‍♂️
    -0.46
    valentino
    -0.46
    ContentValues
    -0.46
    POSITIVE LOGITS
     secundario
    0.43
     للاسماء
    0.40
     rodillas
    0.40
     habido
    0.40
     cementerio
    0.38
     secundaria
    0.38
     hidráulica
    0.37
     producciones
    0.35
     profundidad
    0.35
     asociados
    0.35
    Act Density 0.045%

    No Known Activations