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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts and functionalities related to methods and message handling in a library, particularly in a Protobuf context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pla
    -0.42
    Cu
    -0.37
     Pla
    -0.36
     Griff
    -0.36
     Burton
    -0.35
     Strick
    -0.35
     Karp
    -0.35
     מו
    -0.35
    inden
    -0.35
     thought
    -0.35
    POSITIVE LOGITS
     pleaſure
    0.74
     faſt
    0.71
     ſta
    0.71
     perſon
    0.71
     leſs
    0.68
    ContentAsync
    0.68
     tranſ
    0.67
     Roskov
    0.66
    wiſe
    0.66
     cauſe
    0.65
    Act Density 0.009%

    No Known Activations