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

    Neuronpedia

    INDEX
    Explanations

    OR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Less
    -0.07
     heuristic
    -0.07
    eth
    -0.07
     minorities
    -0.07
    ETH
    -0.07
     Adler
    -0.07
     tip
    -0.07
     리스트
    -0.07
     tous
    -0.06
    /high
    -0.06
    POSITIVE LOGITS
    .assertIn
    0.06
    것
    0.06
    ...");↵↵
    0.06
    最大
    0.06
     Although
    0.06
     것이
    0.06
     contend
    0.06
    şi
    0.06
     університ
    0.06
     оди
    0.06
    Act Density 0.000%

    No Known Activations