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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to the field of education.

    oai_token-act-pair · gemini-2.0-flash

    teaching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Efq
    -2.95
     Theſe
    -2.88
     myſelf
    -2.78
     Monfieur
    -2.77
     Houſe
    -2.70
     Diſ
    -2.69
     Jefus
    -2.61
     itſelf
    -2.59
     Eſ
    -2.56
     Reſ
    -2.55
    POSITIVE LOGITS
     
    1.80
    .
    1.77
     (
    1.69
    ,
    1.64
      
    1.62
     I
    1.39
    ↵
    1.37
    <eos>
    1.37
     B
    1.28
     T
    1.27
    Act Density 3.149%

    No Known Activations