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

    Neuronpedia

    INDEX
    Explanations

    time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    問
    -0.07
    ipe
    -0.07
     grill
    -0.07
     Coff
    -0.06
     servi
    -0.06
     chatter
    -0.06
     coach
    -0.06
    Tes
    -0.06
     cuisine
    -0.06
     theater
    -0.06
    POSITIVE LOGITS
    .walk
    0.07
     Россий
    0.07
     irresistible
    0.07
    Privacy
    0.07
    0.06
     неп
    0.06
      ↵    ↵
    0.06
     ط
    0.06
     şarkı
    0.06
     overriding
    0.06
    Act Density 0.035%

    No Known Activations