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

    Neuronpedia

    INDEX
    Explanations

    gravity pulls Earth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    drawingCode
    0.50
    ictionnaire
    0.49
    🥊
    0.49
     manipulations
    0.49
     하였다
    0.49
    🥙
    0.49
     ዘዴ
    0.49
    StarGo
    0.48
     giocando
    0.48
    㬶
    0.48
    POSITIVE LOGITS
     for
    0.54
    0.52
     See
    0.47
     Sports
    0.46
     Spor
    0.46
    for
    0.46
     OF
    0.46
     THREE
    0.45
     COS
    0.45
     H
    0.45
    Act Density 0.006%

    No Known Activations