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

    Neuronpedia

    INDEX
    Explanations

    advanced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (userInfo
    -0.08
    rador
    -0.07
     vid
    -0.07
    fried
    -0.06
    HECK
    -0.06
     Niet
    -0.06
    Wil
    -0.06
     Kok
    -0.06
    @Test
    -0.06
    들을
    -0.06
    POSITIVE LOGITS
    𣷭
    0.08
    黄瓜
    0.07
    흙
    0.07
    قواعد
    0.07
    ﾓ
    0.07
    _compiler
    0.07
    赜
    0.07
    ۓ
    0.07
    -builder
    0.07
    вшис
    0.07
    Act Density 0.001%

    No Known Activations