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

    Neuronpedia

    INDEX
    Explanations

    cloud services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     მაგრამ
    0.41
    第五
    0.40
    ждый
    0.40
    ச்சத்து
    0.39
    章节
    0.39
     Mục
    0.39
     ऑर्गे
    0.38
    第六
    0.38
    境界層
    0.38
     Uncertainty
    0.38
    POSITIVE LOGITS
    ru
    0.41
    Tam
    0.41
     dor
    0.39
    Charlotte
    0.39
    IK
    0.38
    hle
    0.38
    image
    0.36
     Buccaneers
    0.36
    umar
    0.36
     Marco
    0.36
    Act Density 0.000%

    No Known Activations