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

    Neuronpedia

    INDEX
    Explanations

    this is where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    當然
    0.49
     oczywiście
    0.46
     лишь
    0.44
    もちろん
    0.42
     más
    0.42
     ovviamente
    0.42
     liturg
    0.42
     évidemment
    0.41
     savent
    0.41
     memang
    0.40
    POSITIVE LOGITS
    有两种
    0.51
     FOUR
    0.50
    为了
    0.47
    ・
    0.47
     Upon
    0.47
     EACH
    0.47
     Unlike
    0.46
     IMPORTANT
    0.46
     IMMEDI
    0.46
    以下の
    0.43
    Act Density 0.130%

    No Known Activations