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

    Neuronpedia

    INDEX
    Explanations

    rather than without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ikke
    0.42
     allerede
    0.42
     unterwegs
    0.41
    وم
    0.41
     pourrez
    0.40
     perfekt
    0.39
     parfait
    0.37
     สามารถ
    0.37
     травня
    0.37
     einiger
    0.37
    POSITIVE LOGITS
     properly
    0.53
     adequately
    0.49
     призна
    0.45
    真正的
    0.45
     bothered
    0.43
     Properly
    0.42
     proper
    0.41
     recognise
    0.41
    proper
    0.41
     adequ
    0.40
    Act Density 0.128%

    No Known Activations