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

    Neuronpedia

    INDEX
    Explanations

    titles of people in charge

    oai_token-act-pair · gemini-2.0-flash

    chief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -2.27
    ſelf
    -2.14
     Monfieur
    -2.14
     myſelf
    -2.14
    ſelves
    -2.09
     Theſe
    -2.05
     Majefty
    -2.05
     Jefus
    -1.98
     itſelf
    -1.93
     auffi
    -1.88
    POSITIVE LOGITS
    ↵↵
    1.52
     
    1.42
    ↵
    1.21
    <eos>
    1.20
      
    1.18
    1
    1.16
    2
    1.14
     (
    1.12
    3
    1.07
     I
    1.06
    Act Density 1.267%

    No Known Activations