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

    Neuronpedia

    INDEX
    Explanations

    Swipe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jan
    -0.09
    Jan
    -0.09
     whereabouts
    -0.08
     jan
    -0.08
     mirac
    -0.08
     Pentec
    -0.07
     gatherings
    -0.07
     December
    -0.07
    urable
    -0.07
    irty
    -0.07
    POSITIVE LOGITS
    -through
    0.10
     вверх
    0.09
     adelante
    0.09
     attraverso
    0.08
     عبر
    0.08
    れ
    0.08
     Personas
    0.08
     вперед
    0.08
     ચુક
    0.08
     ખે
    0.07
    Act Density 0.004%

    No Known Activations