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

    Neuronpedia

    INDEX
    Explanations

    ester product hum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lož
    0.52
    ON
    0.50
    one
    0.49
     š
    0.49
    der
    0.48
     în
    0.47
     kontrol
    0.47
    ní
    0.46
    kont
    0.46
     sme
    0.46
    POSITIVE LOGITS
    щі
    0.46
    зіно
    0.45
     asymptotics
    0.45
    ल्लिंग
    0.44
    ድረግ
    0.43
    锆
    0.43
     clears
    0.43
    不能为空
    0.43
    ፅ
    0.43
     pSig
    0.42
    Act Density 0.002%

    No Known Activations