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

    Neuronpedia

    INDEX
    Explanations

    Large Language Model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bulletins
    0.46
     innovations
    0.42
    鶚
    0.41
    ㄙ
    0.41
     kilos
    0.40
     बूंद
    0.40
     Injuries
    0.39
    を示
    0.39
     martens
    0.39
    リスク
    0.39
    POSITIVE LOGITS
    ısına
    0.45
    angka
    0.45
    ыска
    0.45
     Pursuant
    0.45
     utterly
    0.44
    adım
    0.43
     이용
    0.43
     গবে
    0.43
     ignorant
    0.43
    stwa
    0.42
    Act Density 0.009%

    No Known Activations