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

    Neuronpedia

    INDEX
    Explanations

    vehicles and aircraft

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.50
    as
    0.45
    지
    0.43
    to
    0.41
    are
    0.38
    the
    0.36
    𝗱
    0.36
    is
    0.33
    i
    0.33
    г
    0.32
    POSITIVE LOGITS
     Fahrzeuge
    0.33
     ATV
    0.32
     vybaven
    0.32
     gesund
    0.32
     ausgel
    0.31
    燹
    0.30
     ولكن
    0.30
     appareils
    0.30
     ausgestattet
    0.30
     لكن
    0.29
    Act Density 0.138%

    No Known Activations