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

    Neuronpedia

    INDEX
    Explanations

    Box, algorithms, game code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PositionY
    0.53
     کرا
    0.47
    QTTR
    0.46
     apenas
    0.45
     Micron
    0.45
    일까지
    0.45
     envolv
    0.44
    Ordered
    0.44
    ос
    0.43
     edizione
    0.43
    POSITIVE LOGITS
     transposition
    0.48
    human
    0.47
     polymorphism
    0.47
     कारण
    0.46
    不利
    0.46
     thug
    0.44
     shunt
    0.44
    rib
    0.43
     matte
    0.42
    重要的是
    0.42
    Act Density 0.000%

    No Known Activations