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

    Neuronpedia

    INDEX
    Explanations

    sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لى
    -0.06
     новые
    -0.06
    б
    -0.06
    з
    -0.06
    质
    -0.06
     Gear
    -0.06
    _Node
    -0.06
    fails
    -0.06
     її
    -0.06
    ś
    -0.06
    POSITIVE LOGITS
    哪
    0.07
    üme
    0.06
    meyen
    0.06
     @{↵
    0.06
    318
    0.06
     -*-↵↵
    0.06
          ↵      ↵
    0.06
     omnip
    0.06
     approving
    0.06
    후기
    0.06
    Act Density 0.001%

    No Known Activations