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

    Neuronpedia

    INDEX
    Explanations

    could you tell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     soaring
    0.44
     beginnings
    0.44
    ພວກເຮົາ
    0.42
     まず
    0.40
    まずは
    0.40
    kbar
    0.39
     altogether
    0.39
     首先
    0.39
     simply
    0.38
    首先
    0.38
    POSITIVE LOGITS
     considère
    0.53
     berücksichtigt
    0.49
     иногда
    0.48
    考虑
    0.48
    Inform
    0.47
     추가
    0.46
    考慮
    0.46
    engel
    0.45
     informée
    0.44
    Beware
    0.44
    Act Density 0.000%

    No Known Activations