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

    Neuronpedia

    INDEX
    Explanations

    the word "sentence" and words associated with legal proceedings

    oai_token-act-pair · gemini-2.0-flash

    sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     a
    -0.89
     an
    -0.82
     some
    -0.81
     var
    -0.81
     can
    -0.79
     am
    -0.77
     the
    -0.77
     all
    -0.76
     er
    -0.76
     standard
    -0.75
    POSITIVE LOGITS
     itſelf
    1.42
     myſelf
    1.19
     Efq
    1.13
     Monfieur
    1.12
     Jefus
    1.12
     negroes
    1.12
    Tembelea
    1.12
     pleaſure
    1.11
     Shakspeare
    1.09
     ſche
    1.09
    Act Density 3.013%

    No Known Activations