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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to experimental processes and methodologies

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

    Values or quantities, possibly numerical

    np_acts-logits-general · gemini-2.0-flash

    measures or states were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.84
    DoubleQuotes
    -0.81
     فريبيس
    -0.80
     متعلقه
    -0.79
     незавершена
    -0.79
    LEncoder
    -0.78
     الحره
    -0.78
     ujednoznacz
    -0.76
    İstinadlar
    -0.75
    AddHtmlAttribute
    -0.73
    POSITIVE LOGITS
     approximately
    1.38
     $
    1.24
     £
    1.23
     sebesar
    1.23
     
    1.17
     Approximately
    1.16
     approx
    1.14
    approximately
    1.10
     حوالي
    1.10
     yaklaşık
    1.09
    Act Density 2.894%

    No Known Activations