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

    Neuronpedia

    INDEX
    Explanations

    dynamic followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    1.23
    ATE
    1.01
    I
    1.00
    AI
    0.99
    ENT
    0.95
    的消息
    0.94
    6
    0.94
    ated
    0.93
    AV
    0.93
    的需求
    0.92
    POSITIVE LOGITS
    на
    1.30
    ک
    1.22
    리
    1.19
    یم
    1.16
    າມາດ
    1.13
     njih
    1.12
    มัน
    1.12
     criou
    1.08
    त
    1.08
    ۰
    1.06
    Act Density 0.031%

    No Known Activations