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

    Neuronpedia

    INDEX
    Explanations

    words relating to chemical or industrial processes, and some foreign verb conjugations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.92
     myſelf
    -0.91
     themſelves
    -0.90
     itſelf
    -0.89
     himſelf
    -0.86
     Reſ
    -0.84
     Theſe
    -0.84
     ſhall
    -0.81
     Monfieur
    -0.81
     fometimes
    -0.80
    POSITIVE LOGITS
    /*
    0.87
     NSCoder
    0.82
    endphp
    0.74
    ]")]
    0.74
     AssemblyCulture
    0.71
    baye
    0.69
     parseFrom
    0.68
    //</
    0.66
    føl
    0.66
    astify
    0.66
    Act Density 1.922%

    No Known Activations