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

    Neuronpedia

    INDEX
    Explanations

    instances and examples in the text

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

    for example, for instance, in particular

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.47
    帖最后由
    -0.47
    Ծանոթ
    -0.46
     sumpay
    -0.42
     Worker
    -0.41
    tahui
    -0.39
    jamientos
    -0.38
     memoized
    -0.38
    qtype
    -0.38
     Zust
    -0.38
    POSITIVE LOGITS
    FirstResponder
    0.59
     NSCoder
    0.52
    IsPostBack
    0.45
     الحره
    0.45
    middels
    0.44
     vaiz
    0.43
     الرياضيه
    0.42
     OMITBAD
    0.42
    ConfigureAwait
    0.42
    лтемелер
    0.41
    Act Density 0.015%

    No Known Activations