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

    Neuronpedia

    INDEX
    Explanations

    rhyming lyrics.

    oai_token-act-pair · gemini-2.0-flash

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.75
     grand
    -0.47
    ikas
    -0.45
     Red
    -0.44
    nius
    -0.43
     T
    -0.43
     k
    -0.43
     []:
    -0.42
    etu
    -0.42
    tis
    -0.41
    POSITIVE LOGITS
     itſelf
    0.88
     reaſon
    0.84
     myſelf
    0.80
     becauſe
    0.77
     reafon
    0.75
     Shakspeare
    0.73
    richTextPanel
    0.72
    Література
    0.71
     themſelves
    0.71
     cauſe
    0.70
    Act Density 0.261%

    No Known Activations