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

    Neuronpedia

    INDEX
    Explanations

    parentheses/commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Merge
    -0.07
     slipped
    -0.07
    olk
    -0.06
    تمكن
    -0.06
    ocado
    -0.06
     hatten
    -0.06
    دخول
    -0.06
    with
    -0.06
    Bru
    -0.06
     Fixture
    -0.06
    POSITIVE LOGITS
    你不
    0.07
     customizable
    0.07
    长大了
    0.07
    Vertical
    0.07
     Initi
    0.06
    ᴅ
    0.06
     flexible
    0.06
    /id
    0.06
    尽情
    0.06
    𝖖
    0.06
    Act Density 0.005%

    No Known Activations