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

    Neuronpedia

    INDEX
    Explanations

    code arguments and messages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IPv
    -0.08
     tevoren
    -0.08
     существует
    -0.07
     образ
    -0.07
     квадрат
    -0.07
     square
    -0.07
     acet
    -0.07
     Gall
    -0.07
    ously
    -0.07
     cater
    -0.07
    POSITIVE LOGITS
    ={↵
    0.08
    ={{↵
    0.08
    >({↵
    0.08
    ={[↵
    0.07
    ={[
    0.07
     없음
    0.07
    ':
    0.07
    criminal
    0.07
    dc
    0.07
    、《
    0.07
    Act Density 0.002%

    No Known Activations