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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بسیاری
    -0.07
     ผ
    -0.06
    اليا
    -0.06
    اپیم
    -0.06
    _strdup
    -0.06
    mb
    -0.06
    _TWO
    -0.06
    �
    -0.06
     oran
    -0.06
    英語
    -0.06
    POSITIVE LOGITS
    元素
    0.07
    ,state
    0.06
     Orient
    0.06
     bitcoin
    0.06
    _re
    0.06
     Admir
    0.06
    189
    0.06
     Valerie
    0.06
     element
    0.06
     REGISTER
    0.06
    Act Density 0.008%

    No Known Activations