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

    Neuronpedia

    INDEX
    Explanations

    ri

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enso
    -0.06
     volunt
    -0.06
     tématu
    -0.06
    Nut
    -0.06
     alloy
    -0.06
     systemctl
    -0.06
    .vol
    -0.06
     par
    -0.06
    -layer
    -0.06
     stimulates
    -0.06
    POSITIVE LOGITS
    inoa
    0.14
     aph
    0.14
     Aph
    0.07
    米
    0.07
      
↵
↵
    0.06
    'b
    0.06
    ам
    0.06
    AP
    0.06
    	  ↵
    0.06
    と思う
    0.06
    Act Density 0.003%

    No Known Activations