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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     componentWillMount
    -0.06
     nhớ
    -0.06
    *******
    -0.06
    ough
    -0.06
    اری
    -0.06
     ترین
    -0.06
     perce
    -0.06
     γνω
    -0.06
     Mans
    -0.06
    보내기
    -0.06
    POSITIVE LOGITS
    σκε
    0.07
     Dinner
    0.06
    gl
    0.06
     развити
    0.06
    Mc
    0.06
     nowhere
    0.06
    �
    0.06
     Imm
    0.06
     입
    0.06
     việc
    0.06
    Act Density 0.019%

    No Known Activations