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

    Neuronpedia

    INDEX
    Explanations

    Original

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROUTE
    -0.06
     Algebra
    -0.06
     CTL
    -0.06
    ۳۵
    -0.06
    TOP
    -0.06
     MJ
    -0.06
    set
    -0.06
     decorating
    -0.06
    част
    -0.06
    _operator
    -0.06
    POSITIVE LOGITS
    TableName
    0.07
     благод
    0.07
    .partial
    0.07
     original
    0.06
    .Gradient
    0.06
     og
    0.06
     [](
    0.06
    querque
    0.06
     chemicals
    0.06
     Rever
    0.06
    Act Density 0.003%

    No Known Activations