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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating complexity or difficulty

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

    dictated by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.72
     queſta
    -0.67
    SharedCtor
    -0.61
     Италијани
    -0.60
    :✨
    -0.57
    PerformLayout
    -0.57
    oredCriteria
    -0.57
     AppCompatTheme
    -0.54
    ➯
    -0.53
    tisgarh
    -0.49
    POSITIVE LOGITS
    sa
    0.45
     تضيفلها
    0.41
    -
    0.39
    ome
    0.39
    f
    0.38
    ss
    0.38
    sy
    0.36
    ym
    0.36
    ngan
    0.36
    s
    0.36
    Act Density 0.286%

    No Known Activations