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

    Neuronpedia

    INDEX
    Explanations

    requests for descriptions or explanations

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

    asking to describe or explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.71
    ]")]
    -0.58
     consuma
    -0.54
     الحره
    -0.53
    providedIn
    -0.52
    Спасылкі
    -0.52
    EndContext
    -0.52
    parsedMessage
    -0.52
     radiators
    -0.51
    IMPORTED
    -0.50
    POSITIVE LOGITS
    Describe
    1.13
     Describe
    1.09
     Explain
    0.81
    Explain
    0.79
     Discuss
    0.68
    Discuss
    0.66
    describe
    0.61
    WaitGroup
    0.43
     gimana
    0.41
    谈
    0.40
    Act Density 0.033%

    No Known Activations