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

    Neuronpedia

    INDEX
    Explanations

    media genres and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    的任务
    0.57
    Node
    0.55
    Resources
    0.54
    ಕೆಯ
    0.54
    修改
    0.54
    的模型
    0.53
    jeć
    0.53
    的问题
    0.52
     computationally
    0.52
     टिश्यू
    0.52
    POSITIVE LOGITS
     format
    1.06
     style
    0.96
     extravaganza
    0.86
     stalwart
    0.82
     prowess
    0.81
     mainstay
    0.78
    style
    0.77
     genre
    0.77
    スタイル
    0.76
     powerhouse
    0.75
    Act Density 0.513%

    No Known Activations