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

    Neuronpedia

    INDEX
    Explanations

    references to small and simple items or concepts

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

    simple or small things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.42
    GEBURTSDATUM
    -0.41
    KommentareTeilen
    -0.41
     StatefulWidget
    -0.40
     defStyleAttr
    -0.38
    penup
    -0.38
    makeConstraints
    -0.35
     mélang
    -0.35
     /\.
    -0.33
     trachea
    -0.32
    POSITIVE LOGITS
     simply
    0.56
    simply
    0.52
     OMITBAD
    0.52
     mergeFrom
    0.52
     simplemente
    0.51
     صوتيه
    0.51
    AndEndTag
    0.51
    Simply
    0.50
     simplest
    0.50
     simpel
    0.49
    Act Density 0.030%

    No Known Activations