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

    Neuronpedia

    INDEX
    Explanations

    quotes and dialogue in the text

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

    dialogue start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Picchu
    -0.39
    ContentAlignment
    -0.37
    Vege
    -0.35
     gevallen
    -0.34
     okuyayım
    -0.33
     swe
    -0.33
     Bren
    -0.33
    utnant
    -0.32
     risico
    -0.31
    daß
    -0.31
    POSITIVE LOGITS
     Мексичка
    0.57
    SuppressLint
    0.53
     المعيارى
    0.51
     Perſ
    0.50
     defaultstate
    0.50
     للمعارف
    0.49
     transférez
    0.49
     protoimpl
    0.49
    AnimationsModule
    0.48
     onCancelled
    0.47
    Act Density 0.074%

    No Known Activations