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

    Neuronpedia

    INDEX
    Explanations

    the word "but."

    oai_token-act-pair · gemini-2.0-flash

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.68
     ujednoznacz
    -0.66
    SharedCtor
    -0.65
     ſmall
    -0.64
     pleaſure
    -0.63
     myſelf
    -0.63
     Diſ
    -0.63
     Jefus
    -0.62
     purpoſe
    -0.62
     theſe
    -0.60
    POSITIVE LOGITS
    psons
    0.52
    USTER
    0.43
     birth
    0.43
    /***/
    0.41
     AssemblyCulture
    0.40
     Ala
    0.40
     Juga
    0.39
    DebuggerStep
    0.39
    erto
    0.39
     multiple
    0.39
    Act Density 0.192%

    No Known Activations