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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets, and list delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    touchstart
    0.38
     रिएक्टर
    0.37
    䂙
    0.37
    icientes
    0.36
     ற
    0.36
    PageRoute
    0.35
    StartY
    0.35
    स्टर
    0.35
    шон
    0.35
    reflectionCamera
    0.34
    POSITIVE LOGITS
     baja
    0.38
     umano
    0.38
     tir
    0.37
     形
    0.36
     ২
    0.36
     baix
    0.35
    Tai
    0.35
     concede
    0.34
    <0x91>
    0.34
     addr
    0.34
    Act Density 0.001%

    No Known Activations