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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harris
    -0.08
     periodic
    -0.08
    Roots
    -0.08
     dancers
    -0.08
     explorers
    -0.07
     själva
    -0.07
     réellement
    -0.07
    roots
    -0.07
     Seeds
    -0.07
     sonder
    -0.07
    POSITIVE LOGITS
    uer
    0.08
     supervising
    0.08
    letter
    0.08
     résumé
    0.08
     ஆகிய
    0.08
     મને
    0.08
     multil
    0.08
     ※
    0.08
    "↵↵↵↵
    0.08
    -letter
    0.07
    Act Density 0.120%

    No Known Activations