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

    Neuronpedia

    INDEX
    Explanations

    -stage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کسب
    -0.07
     Said
    -0.07
     освіти
    -0.07
     işlet
    -0.06
     Imper
    -0.06
    _signals
    -0.06
     paving
    -0.06
     chiều
    -0.06
     znal
    -0.06
     lông
    -0.06
    POSITIVE LOGITS
    xE
    0.06
    ANGUAGE
    0.06
    ۴
    0.06
     ){
↵
    0.06
    ondrous
    0.06
    [](
    0.06
     hive
    0.06
    лл
    0.05
    347
    0.05
    ，此
    0.05
    Act Density 0.067%

    No Known Activations