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

    Neuronpedia

    INDEX
    Explanations

    email addresses mentioned in the text

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

    email address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.52
     صوتيه
    -0.52
    IntoConstraints
    -0.51
     esternos
    -0.50
    Tembelea
    -0.49
    Aholisi
    -0.45
    ThemeOverlay
    -0.45
    interference
    -0.44
    ViewFeatures
    -0.43
     فريبيس
    -0.43
    POSITIVE LOGITS
    ęb
    0.39
     musicales
    0.36
     lautet
    0.36
    didSet
    0.35
    SequentialGroup
    0.35
     foncé
    0.35
     EconPapers
    0.34
     Vernunft
    0.34
    es
    0.34
     Pflicht
    0.34
    Act Density 0.007%

    No Known Activations