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

    Neuronpedia

    INDEX
    Explanations

    around the world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    简直
    0.43
     filmmaking
    0.41
     წარმო
    0.41
    0.41
    ᅢ
    0.40
     ซึ่ง
    0.40
     barbaric
    0.40
    そも
    0.39
     Fähigkeiten
    0.39
    ซึ่ง
    0.39
    POSITIVE LOGITS
     on
    0.52
     ở
    0.52
     around
    0.46
     near
    0.45
     of
    0.45
     from
    0.44
    7
    0.44
     فى
    0.43
     at
    0.42
     районов
    0.42
    Act Density 0.026%

    No Known Activations