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

    Neuronpedia

    INDEX
    Explanations

    the definite article "the"

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

    On the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.61
    afficheront
    -0.59
    发表于
    -0.57
    ########.
    -0.56
    RegressionTest
    -0.54
    reportWebVitals
    -0.51
     wikipagina
    -0.51
     HasFactory
    -0.50
     незавершена
    -0.49
    tanleria
    -0.47
    POSITIVE LOGITS
     on
    0.91
     On
    0.71
     ON
    0.65
     på
    0.63
     trên
    0.61
     روی
    0.61
    On
    0.58
     onStart
    0.57
    OnThe
    0.57
    onthe
    0.55
    Act Density 0.094%

    No Known Activations