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

    Neuronpedia

    INDEX
    Explanations

    critical commentary on societal norms and beliefs

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

    ! ? punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.93
     дописавши
    -0.80
     nahilalakip
    -0.79
    Personendaten
    -0.78
    oa̍t
    -0.77
     يتيمه
    -0.77
     disambiguazione
    -0.72
    IVEREF
    -0.72
     initComponents
    -0.71
    :✨
    -0.68
    POSITIVE LOGITS
    eraard
    0.40
    !
    0.35
    ?!
    0.34
     VERY
    0.34
     yoktur
    0.33
    !!
    0.33
    !)
    0.32
    !!!
    0.32
    !).
    0.31
     yoksa
    0.30
    Act Density 0.476%

    No Known Activations