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

    Neuronpedia

    INDEX
    Explanations

    car

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     મહિલ
    -0.09
     પ્રાપ્ત
    -0.08
     സ്ത്രീ
    -0.08
    female
    -0.08
     받
    -0.08
     여성
    -0.08
     വനിത
    -0.08
     મહિલા
    -0.08
     રાખ
    -0.08
     recebeu
    -0.08
    POSITIVE LOGITS
     gemeinsam
    0.11
     Gemeinsam
    0.10
     gemeinsame
    0.10
     gemeinsamen
    0.10
     gemeins
    0.08
     hiking
    0.08
     juntos
    0.08
     vacations
    0.08
    一起
    0.08
     shaker
    0.08
    Act Density 0.062%

    No Known Activations