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

    Neuronpedia

    INDEX
    Explanations

    get data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ractical
    0.44
    Thinking
    0.44
     grammat
    0.40
    recated
    0.40
     Thinking
    0.39
    thinking
    0.39
    perme
    0.38
    NOTA
    0.38
     thinking
    0.37
     ഊ
    0.37
    POSITIVE LOGITS
     getAll
    0.55
     获取
    0.54
     login
    0.52
    查詢
    0.51
     find
    0.51
    JsonResponse
    0.49
     sessionId
    0.49
    查找
    0.49
    を取得
    0.49
     get
    0.48
    Act Density 0.032%

    No Known Activations