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

    Neuronpedia

    INDEX
    Explanations

    convex optimization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     குர
    0.49
    t
    0.49
     linguistique
    0.48
    VOA
    0.48
    ل
    0.47
     اللغه
    0.47
    tics
    0.47
     amplify
    0.46
    वाज
    0.45
     yao
    0.45
    POSITIVE LOGITS
    蒞
    0.45
    diği
    0.45
    រយៈ
    0.42
    enuhi
    0.42
    вому
    0.41
    धील
    0.39
    ↵
    0.39
     також
    0.39
    äft
    0.38
    cellaneous
    0.38
    Act Density 0.110%

    No Known Activations