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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or emphasis in dialogue

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

    Quotation marks and apostrophes

    np_acts-logits-general · gemini-2.0-flash

    opening quotes or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endregion
    -0.45
    page
    -0.45
    mocked
    -0.42
    bewerken
    -0.42
    dieu
    -0.40
    зите
    -0.40
     kendisi
    -0.39
    fon
    -0.39
    مصادر
    -0.39
     للمعارف
    -0.39
    POSITIVE LOGITS
    __*/
    0.85
     hey
    0.74
     morire
    0.73
    BufferException
    0.71
    новниш
    0.69
     kyllä
    0.69
     Hey
    0.69
     yep
    0.68
    hey
    0.64
     wow
    0.64
    Act Density 0.099%

    No Known Activations