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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hat
    -0.07
    Uri
    -0.07
    <Document
    -0.07
     manager
    -0.06
    .Argument
    -0.06
    /portfolio
    -0.06
     öld
    -0.06
    Entropy
    -0.06
    Population
    -0.06
    erosis
    -0.06
    POSITIVE LOGITS
    .NewLine
    0.07
     продукты
    0.06
     व
    0.06
     пере
    0.06
    集合
    0.06
     есть
    0.06
    .GetService
    0.06
    なんて
    0.06
    �
    0.06
     пол
    0.06
    Act Density 0.002%

    No Known Activations