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

    Neuronpedia

    INDEX
    Explanations

    emojis 🌽 💰

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ти
    1.63
    ट
    1.38
    ت
    1.35
    𝑠
    1.34
     anos
    1.22
     investimentos
    1.21
     serviços
    1.21
     एका
    1.18
    ス
    1.18
    イヤ
    1.17
    POSITIVE LOGITS
    اء
    1.58
     Underwater
    1.53
     മരണ
    1.52
    drawn
    1.49
    два
    1.47
    cknowled
    1.45
     maxX
    1.42
    ELE
    1.40
    ँव
    1.39
     chameleon
    1.39
    Act Density 0.000%

    No Known Activations