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

    Neuronpedia

    INDEX
    Explanations

    response context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Signaling
    0.48
     Consistency
    0.48
    数据
    0.46
     Sulfur
    0.44
    ⛔
    0.44
    ляется
    0.44
     ㅅ
    0.44
    を作成
    0.43
     ไม่
    0.43
    いわ
    0.43
    POSITIVE LOGITS
    ünkü
    0.49
     weekends
    0.48
     urgently
    0.46
     fallait
    0.46
    akot
    0.46
     svě
    0.45
     weekend
    0.45
     extraordin
    0.44
     couches
    0.44
     cottages
    0.43
    Act Density 0.000%

    No Known Activations