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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amate
    -0.08
    ursors
    -0.08
     constru
    -0.07
     friction
    -0.07
     painstaking
    -0.07
    azines
    -0.07
    mt
    -0.07
     veloc
    -0.07
    sentence
    -0.07
     Buddhism
    -0.07
    POSITIVE LOGITS
    เร
    0.08
    rẹ
    0.08
     Nga
    0.08
    ోంది
    0.08
     обход
    0.07
    െയാണ്
    0.07
    ర్న
    0.07
     વેપ
    0.07
     suspicious
    0.07
     danh
    0.07
    Act Density 0.005%

    No Known Activations