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

    Neuronpedia

    INDEX
    Explanations

    various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    如图
    0.45
     pictured
    0.44
    图
    0.43
     Picard
    0.41
    如下图
    0.41
    imageData
    0.41
    圖
    0.41
     afbeelding
    0.40
    圖片
    0.39
    uments
    0.39
    POSITIVE LOGITS
     व्याव
    0.42
     меч
    0.40
    夢
    0.40
    NAN
    0.39
    меч
    0.38
    ibal
    0.38
    Fan
    0.38
     FAN
    0.37
     θε
    0.37
     acuerdos
    0.37
    Act Density 0.000%

    No Known Activations