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

    Neuronpedia

    INDEX
    Explanations

    who that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itm
    -0.07
     item
    -0.07
    CHASE
    -0.07
     résultats
    -0.06
    .rl
    -0.06
     DW
    -0.06
    rt
    -0.06
    chap
    -0.06
    usses
    -0.06
    aphael
    -0.06
    POSITIVE LOGITS
    obody
    0.07
     गलत
    0.07
     objectively
    0.07
     hát
    0.07
     кус
    0.07
    -src
    0.06
     лекар
    0.06
     неб
    0.06
     तब
    0.06
    	LEFT
    0.06
    Act Density 0.093%

    No Known Activations