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

    Neuronpedia

    INDEX
    Explanations

    when verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     إذا
    0.37
     বেশকিছু
    0.35
     बखूबी
    0.33
     אם
    0.33
     सहित
    0.32
    imper
    0.32
     nonché
    0.32
     wenn
    0.31
     whose
    0.31
    _.
    0.31
    POSITIVE LOGITS
    ၊
    0.38
     তখন
    0.37
     очередной
    0.36
     xong
    0.34
     វា
    0.33
    ,【
    0.33
     inevitably
    0.33
     сталки
    0.33
    ，「
    0.32
    хие
    0.32
    Act Density 0.096%

    No Known Activations