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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating judgment or assertion about actions

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

    academic study or publications

    np_acts-logits-general · gemini-2.0-flash

    scholarly book or text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     azioni
    -0.55
     duyg
    -0.55
     kejadian
    -0.51
     espri
    -0.51
    chkin
    -0.49
     hikay
    -0.48
     imparare
    -0.47
     Entrepreneur
    -0.47
     fratelli
    -0.47
     emozioni
    -0.46
    POSITIVE LOGITS
     scholarly
    1.04
     scholars
    1.01
     scholar
    0.90
     bibliography
    0.89
     scholarship
    0.87
    Scholars
    0.81
    scholars
    0.79
    Personendaten
    0.76
    scholar
    0.74
     historians
    0.74
    Act Density 0.367%

    No Known Activations