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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    small
    -0.07
     BEST
    -0.07
     lb
    -0.06
     Options
    -0.06
     small
    -0.06
     decorator
    -0.06
    extras
    -0.06
     preceding
    -0.06
     matrices
    -0.06
    rq
    -0.06
    POSITIVE LOGITS
    AutoSize
    0.08
     newPos
    0.07
     demok
    0.07
    ячи
    0.07
    모
    0.07
    걸
    0.07
    切
    0.07
    .Formatting
    0.07
    ož
    0.06
     또
    0.06
    Act Density 0.101%

    No Known Activations