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

    Neuronpedia

    INDEX
    Explanations

    questions and conditional statements

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

    Answers beginning with "yes" or "yeah"

    np_acts-logits-general · gemini-2.0-flash

    affirmations and negations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apore
    -0.52
    ınca
    -0.49
    anía
    -0.48
    ungle
    -0.47
    )|^{
    -0.46
    }")]
    -0.45
     Bourgoin
    -0.44
    arate
    -0.44
    ßerdem
    -0.44
    öng
    -0.43
    POSITIVE LOGITS
     yes
    3.81
     Yes
    3.39
    Yes
    3.28
    yes
    3.11
     YES
    2.97
    YES
    2.68
     yeah
    2.48
     yep
    2.19
     Yeah
    2.18
     Yep
    2.09
    Act Density 0.692%

    No Known Activations