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

    Neuronpedia

    INDEX
    Explanations

    fold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sometimes
    -0.06
    .Constraint
    -0.06
    491
    -0.06
     ClassNotFoundException
    -0.06
    905
    -0.06
     Importance
    -0.06
     ClassName
    -0.06
     railways
    -0.06
    .Spec
    -0.06
    _annotations
    -0.06
    POSITIVE LOGITS
    عاد
    0.07
    ЕР
    0.07
    roit
    0.07
     Elekt
    0.06
     чолов
    0.06
    ี
    0.06
    研
    0.06
     SER
    0.06
    YK
    0.06
     Accident
    0.06
    Act Density 0.034%

    No Known Activations