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

    Neuronpedia

    INDEX
    Explanations

    what is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beob
    0.63
    ري
    0.49
     beobachten
    0.47
    ennzeichnet
    0.46
    观察
    0.45
    觀察
    0.44
    зай
    0.43
    MM
    0.42
    Observe
    0.42
    Comparison
    0.42
    POSITIVE LOGITS
     усіх
    0.50
     আইএস
    0.47
     ʼ
    0.46
     остальных
    0.43
     automobiles
    0.43
     представления
    0.42
     unregistered
    0.42
    cet
    0.41
     представление
    0.41
     Cowboy
    0.41
    Act Density 0.001%

    No Known Activations