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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chess
    -0.07
    cola
    -0.07
    ".↵↵↵↵
    -0.07
     scouting
    -0.07
    ầy
    -0.07
    岳阳
    -0.06
    Insensitive
    -0.06
    altimore
    -0.06
    .sprite
    -0.06
    uellement
    -0.06
    POSITIVE LOGITS
    샐
    0.07
     wyb
    0.07
    ération
    0.07
     rectangles
    0.07
     WRONG
    0.07
     sideways
    0.07
    Ϋ
    0.07
     moderately
    0.07
     ratified
    0.07
     حيات
    0.06
    Act Density 0.023%

    No Known Activations