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

    Neuronpedia

    INDEX
    Explanations

    C# code with "set" for properties and sometimes C# code with "see" for project liscences

    oai_token-act-pair · gemini-2.0-flash

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -1.77
     Efq
    -1.74
     itſelf
    -1.70
     houſe
    -1.67
     purpoſe
    -1.66
     pleaſure
    -1.66
     Jefus
    -1.59
     raiſ
    -1.57
     Houſe
    -1.54
    ^(@)
    -1.53
    POSITIVE LOGITS
    ↵
    0.87
    ↵↵
    0.81
    .
    0.79
    ...
    0.73
     (
    0.70
    <eos>
    0.67
     //
    0.67
    ↵↵↵
    0.67
    (
    0.66
    …
    0.66
    Act Density 0.428%

    No Known Activations