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

    Neuronpedia

    INDEX
    Explanations

    technical terms and instructions related to software installation and compilation processes

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

    Chinese negation or modal verbs

    np_acts-logits-general · gemini-2.0-flash

    unable to use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -1.15
    ReusableCell
    -1.13
     CreateTagHelper
    -1.13
    ########.
    -1.06
     Мексичка
    -1.05
     متعلقه
    -1.04
     चीज़ों
    -1.01
     iſt
    -1.00
     Theſe
    -0.96
    contentLoaded
    -0.96
    POSITIVE LOGITS
     in
    0.57
     to
    0.56
     for
    0.54
     via
    0.51
     carefully
    0.51
     from
    0.51
    把
    0.49
     give
    0.47
    向
    0.47
     through
    0.47
    Act Density 0.027%

    No Known Activations