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

    Neuronpedia

    INDEX
    Explanations

    percentage symbols and related numerical values

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

    percentages in width and height

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     llamadas
    -0.36
     obligatorio
    -0.35
     electrico
    -0.35
     dorada
    -0.33
     muñecas
    -0.33
     conocen
    -0.33
     conoce
    -0.33
     colgante
    -0.33
     prohibido
    -0.33
     énon
    -0.32
    POSITIVE LOGITS
    %',
    2.25
    %",
    2.03
    %"
    1.48
    %")
    1.45
    %");
    1.43
    %'
    1.42
    %";
    1.42
    %"),
    1.37
    fromnode
    1.02
    %</
    1.02
    Act Density 0.002%

    No Known Activations