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

    Neuronpedia

    INDEX
    Explanations

    word beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    开始
    0.25
    Acetic
    0.25
    禇
    0.23
    错误
    0.23
    标题
    0.23
    Radius
    0.23
    Điều
    0.23
    রিষ্ঠ
    0.23
    ফ
    0.23
    时间
    0.22
    POSITIVE LOGITS
    '
    0.31
    ’
    0.30
     لأن
    0.25
     sajana
    0.24
    igans
    0.24
     lieber
    0.24
     kantor
    0.23
     খানের
    0.23
    legas
    0.23
     mache
    0.22
    Act Density 0.160%

    No Known Activations