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

    Neuronpedia

    INDEX
    Explanations

    sentences that contain dialogue or quoted speech

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

    Concluding sentences with opinions or quotes

    np_acts-logits-general · gemini-2.0-flash

    affirmations and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "¡
    -0.68
     "¿
    -0.65
     “¿
    -0.61
     meines
    -0.58
     "*
    -0.57
     natin
    -0.57
     "
    -0.57
    rientes
    -0.56
    ioutil
    -0.56
    UrlResolution
    -0.56
    POSITIVE LOGITS
    Indeed
    1.03
     Indeed
    0.87
     indeed
    0.77
    Adds
    0.73
     efectivamente
    0.71
    indeed
    0.70
     inderdaad
    0.67
    Added
    0.62
    的确
    0.60
    ыгана
    0.58
    Act Density 0.072%

    No Known Activations