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

    Neuronpedia

    INDEX
    Explanations

    questions ending in questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !")
    0.46
    想法
    0.44
     ((*
    0.44
    満足
    0.44
    !”,
    0.43
    !",
    0.42
    ⸩
    0.42
    ！）
    0.41
    あり
    0.41
    吉
    0.41
    POSITIVE LOGITS
     asked
    0.70
     asks
    0.65
     inquired
    0.61
     preguntó
    0.61
     pregunta
    0.58
     questions
    0.57
     question
    0.57
    asks
    0.56
    ?.
    0.55
    asked
    0.55
    Act Density 0.014%

    No Known Activations