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

    Neuronpedia

    INDEX
    Explanations

    as such, will not fulfill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িয়োগ
    0.37
    儚
    0.35
    ଜ
    0.34
    humidité
    0.34
    PARTMENT
    0.33
    ঘ্রই
    0.33
    শংস
    0.33
    ຈັດສົ່ງ
    0.33
     использовании
    0.32
    rafpunkte
    0.32
    POSITIVE LOGITS
      
    0.41
    ↵↵
    0.38
    ,
    0.36
     =
    0.35
    ↵
    0.34
     diagonally
    0.33
     de
    0.32
    \
    0.32
     the
    0.31
    //
    0.31
    Act Density 0.361%

    No Known Activations