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

    Neuronpedia

    INDEX
    Explanations

    connective words and phrases that indicate comparisons, contrasts, or continuations in a text

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

    than, but, and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.51
     trône
    -0.48
     doigt
    -0.47
    #+#
    -0.47
     Sénat
    -0.42
     Anſ
    -0.40
    PETS
    -0.40
    səhifə
    -0.40
    WindowConstants
    -0.40
    Trans
    -0.40
    POSITIVE LOGITS
     υπάρχει
    0.42
     habido
    0.42
     onCreate
    0.41
     pitä
    0.41
    \{\\
    0.41
    があって
    0.39
    WithIOException
    0.39
     Klicken
    0.39
     gyhoeddwyd
    0.39
     */,
    0.38
    Act Density 0.124%

    No Known Activations