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

    Neuronpedia

    INDEX
    Explanations

    strong affirmative statements and promotional language

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

    punctuation following sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Spoljašnje
    -0.50
    WriteTagHelper
    -0.50
    WebElementEntity
    -0.47
    WithMany
    -0.47
     ModelExpression
    -0.44
     تعدى
    -0.41
    PMailer
    -0.41
    antaranya
    -0.41
    writeField
    -0.41
    tagext
    -0.40
    POSITIVE LOGITS
     насељу
    0.52
    RefNanny
    0.46
    ViewFeatures
    0.41
     विश्वसनीयता
    0.40
     freue
    0.39
     saurait
    0.38
    owna
    0.38
     Discretion
    0.36
     للاسماء
    0.35
     Spannung
    0.35
    Act Density 0.007%

    No Known Activations