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

    Neuronpedia

    INDEX
    Explanations

    annually

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ুজ
    -0.09
     Uttar
    -0.08
    uline
    -0.08
     juvent
    -0.08
     Richmond
    -0.08
    idlalo
    -0.07
     wooded
    -0.07
     Delhi
    -0.07
    nine
    -0.07
     Uber
    -0.07
    POSITIVE LOGITS
     સરળ
    0.08
     ед
    0.08
     blunt
    0.07
     જોડ
    0.07
     simpl
    0.07
     abstracts
    0.07
     downside
    0.07
     snap
    0.07
     transformations
    0.07
    -अलग
    0.07
    Act Density 0.010%

    No Known Activations