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
    153
    -0.08
    빛
    -0.07
    คน
    -0.07
     Commerce
    -0.07
    _flip
    -0.07
    PGA
    -0.07
     copyright
    -0.06
     CIA
    -0.06
     Submission
    -0.06
     submission
    -0.06
    POSITIVE LOGITS
     swingerclub
    0.07
    .Override
    0.06
     pozem
    0.06
    _COLUMN
    0.06
    ={`/
    0.06
    emade
    0.06
     《
    0.06
     svensk
    0.06
    ...)↵
    0.06
    +"_
    0.06
    Act Density 0.099%

    No Known Activations