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

    Neuronpedia

    INDEX
    Explanations

    German compound words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.86
     It
    0.75
     rifle
    0.72
     refund
    0.72
     government
    0.71
     makeshift
    0.71
     workout
    0.70
     time
    0.70
     pancake
    0.70
     receding
    0.69
    POSITIVE LOGITS
    '=
    0.78
    '
    0.69
    ু
    0.66
    irli
    0.64
     Quadrupèdes
    0.64
    })}\
    0.64
    ٢
    0.61
     乀
    0.60
    '+
    0.59
    '_
    0.59
    Act Density 0.001%

    No Known Activations