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

    Neuronpedia

    INDEX
    Explanations

    words and punctuation marks related to quotes and conversations

    oai_token-act-pair · gemini-2.0-flash

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.98
     itſelf
    -0.96
     avoient
    -0.95
     automatiques
    -0.94
     zelve
    -0.93
     Theſe
    -0.93
     Diſ
    -0.92
     feroit
    -0.91
     Shakspeare
    -0.90
     aveug
    -0.90
    POSITIVE LOGITS
    ↵↵
    0.75
    .
    0.72
     
    0.63
      
    0.62
    “
    0.61
     “
    0.61
    ↵
    0.61
    '
    0.58
    :
    0.58
    ).
    0.58
    Act Density 0.691%

    No Known Activations