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

    Neuronpedia

    INDEX
    Explanations

    controls and limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Heaven
    0.43
     কিছুটা
    0.42
    Alright
    0.41
    뗀
    0.41
     অনেকটাই
    0.41
     ಶಿವ
    0.38
    絶縁
    0.38
    lective
    0.38
    ндан
    0.38
     marsh
    0.37
    POSITIVE LOGITS
    PET
    0.40
     PET
    0.40
     Cit
    0.37
    迁
    0.37
     Spin
    0.35
    gget
    0.34
     মানুষের
    0.33
    工艺
    0.33
     বন্ধুর
    0.33
     ہوئی
    0.33
    Act Density 0.002%

    No Known Activations