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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and closures in code

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

    user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.85
    RenderAtEndOf
    -0.73
    ſelves
    -0.73
     ujednoznacz
    -0.72
    rungsseite
    -0.69
    tanleria
    -0.69
     queſta
    -0.69
    IUrlHelper
    -0.68
     Италијани
    -0.67
     EconPapers
    -0.65
    POSITIVE LOGITS
    2
    0.40
     Hopefully
    0.39
     hopefully
    0.39
     esperado
    0.38
     hizmet
    0.37
     yine
    0.37
    3
    0.37
     ziyaretçi
    0.36
    pustakaan
    0.36
     educativas
    0.36
    Act Density 0.004%

    No Known Activations