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

    Neuronpedia

    INDEX
    Explanations

    punctuated dialog or quotations

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

    citations and article titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.59
     CURIAM
    -0.45
    RenderAtEndOf
    -0.44
     Мексичка
    -0.42
     hieß
    -0.42
     uLocal
    -0.40
    errHandler
    -0.40
     AssemblyCulture
    -0.39
    RegressionTest
    -0.38
     Erwachsenen
    -0.38
    POSITIVE LOGITS
    ✨:
    0.63
    发表于
    0.52
     Pingback
    0.51
    最快更新
    0.50
    fjspx
    0.49
    Hentet
    0.48
    TagMode
    0.43
    ḵ
    0.43
     <<<<<<<<<<<<<<
    0.43
    __);
    0.42
    Act Density 0.100%

    No Known Activations