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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -2.08
    ↵↵
    -1.97
    <eos>
    -1.92
    .
    -1.90
     (
    -1.89
    ↵
    -1.77
    ,
    -1.72
    /
    -1.65
     [
    -1.61
     "
    -1.59
    POSITIVE LOGITS
     myſelf
    4.44
     itſelf
    4.22
     Efq
    4.13
     pleaſure
    3.97
     Jefus
    3.91
     Monfieur
    3.88
     purpoſe
    3.84
     Majefty
    3.84
    ſelf
    3.75
     themſelves
    3.69
    Act Density 2.725%

    No Known Activations