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

    Neuronpedia

    INDEX
    Explanations

    locations on a page

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ificantly
    -1.02
     THROUGH
    -0.99
    铧
    -0.94
    齟
    -0.93
    nables
    -0.92
    ToScroll
    -0.92
    ığımız
    -0.91
    laire
    -0.91
     Scopus
    -0.91
    alism
    -0.86
    POSITIVE LOGITS
     left
    2.08
     right
    1.88
     bottom
    1.46
     top
    1.33
     screen
    1.29
     upper
    1.27
    left
    1.20
    左
    1.20
     справа
    1.16
     next
    1.15
    Act Density 0.064%

    No Known Activations