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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fifo
    -0.07
    _slots
    -0.07
    538
    -0.06
    MAP
    -0.06
    Detector
    -0.06
    neo
    -0.06
     Tulsa
    -0.06
    Pří
    -0.06
     accepting
    -0.06
     неп
    -0.06
    POSITIVE LOGITS
    [V
    0.07
     routers
    0.07
     braking
    0.07
    (Char
    0.06
    (I
    0.06
     를
    0.06
    를
    0.06
    -cons
    0.06
     indis
    0.06
    Stay
    0.06
    Act Density 0.034%

    No Known Activations