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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the beginning of text segments

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

    that start a sentence or clause

    np_acts-logits-general · gemini-2.0-flash

    Introduction, About, When

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entanto
    -1.07
    прочем
    -0.75
     however
    -0.75
     furthermore
    -0.74
    但也
    -0.74
    Revenir
    -0.73
     obstante
    -0.72
    uttavia
    -0.71
    however
    -0.71
     but
    -0.70
    POSITIVE LOGITS
    When
    1.11
     When
    1.08
     Cuando
    0.85
    During
    0.83
     During
    0.83
     Since
    0.82
    Since
    0.81
    After
    0.80
    Sometimes
    0.80
     After
    0.79
    Act Density 0.602%

    No Known Activations