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

    Neuronpedia

    INDEX
    Explanations

    names, contact info, and verbs related to speech and legal proceedings.

    oai_token-act-pair · gemini-2.0-flash

    speech reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ^(@)
    -1.20
    ſelf
    -1.16
     Efq
    -1.14
    ſelves
    -1.13
     myſelf
    -1.13
     Theſe
    -1.12
     Majefty
    -1.09
     itſelf
    -1.09
     Jefus
    -1.04
     themſelves
    -1.02
    POSITIVE LOGITS
    ↵
    0.89
    ↵↵
    0.77
      
    0.66
        
    0.64
    </strong>
    0.64
    "
    0.63
    .
    0.63
    2
    0.62
    A
    0.62
    <sup>
    0.60
    Act Density 2.435%

    No Known Activations