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

    Neuronpedia

    INDEX
    Explanations

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     THEM
    0.49
    다
    0.48
    ᄃ
    0.45
     ठेवा
    0.44
    訛
    0.44
    ו
    0.44
     HIM
    0.43
     ROOM
    0.43
    و
    0.43
     being
    0.43
    POSITIVE LOGITS
     agh
    0.47
     insuff
    0.45
    haul
    0.45
     unang
    0.45
     ഉരു
    0.43
     abre
    0.43
    piele
    0.43
     altern
    0.42
     ইতিমধ্যে
    0.42
    শুক্রবার
    0.42
    Act Density 0.000%

    No Known Activations