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

    Neuronpedia

    INDEX
    Explanations

    percentage values and their formatting within the text

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

    percentages and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cepción
    -0.44
     crees
    -0.42
     varandra
    -0.42
     américains
    -0.41
     cuadros
    -0.40
     communs
    -0.40
     oscuridad
    -0.40
     américa
    -0.40
     spécial
    -0.39
     situación
    -0.39
    POSITIVE LOGITS
    ("%.
    1.80
     %.
    1.66
     {:.
    1.33
    :%.
    1.24
     %).
    0.96
     %-
    0.89
    %.
    0.89
     %),
    0.85
    windowFixed
    0.84
     %,
    0.82
    Act Density 0.009%

    No Known Activations