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

    Neuronpedia

    INDEX
    Explanations

    video lessons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     benzoic
    0.29
    間の
    0.29
     मोठे
    0.29
     کاز
    0.28
    </h3>
    0.27
     वित्तीय
    0.27
     וח
    0.26
     purnama
    0.26
    u
    0.26
    itimate
    0.26
    POSITIVE LOGITS
     Video
    0.33
    Video
    0.32
    گونه
    0.31
     VIDEO
    0.29
     відео
    0.29
    ビデオ
    0.28
    视频
    0.28
    区别
    0.28
    ليو
    0.27
     vídeos
    0.26
    Act Density 0.000%

    No Known Activations