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

    Neuronpedia

    INDEX
    Explanations

    describing question templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dengan
    0.51
     memang
    0.51
     Pusat
    0.49
     체
    0.48
     생
    0.47
     신
    0.46
     tình
    0.46
     실
    0.46
     내
    0.45
    örü
    0.45
    POSITIVE LOGITS
    記述
    0.46
    Describes
    0.43
    പേക്ഷ
    0.43
     correspondence
    0.43
    described
    0.43
     effectual
    0.42
    Transitions
    0.41
    Accessed
    0.41
    "]},{"
    0.41
    FeatureFlags
    0.41
    Act Density 0.005%

    No Known Activations