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

    Neuronpedia

    INDEX
    Explanations

    200 or 201

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tested
    -0.07
     monthly
    -0.07
    락
    -0.06
    سبب
    -0.06
    _er
    -0.06
    温度
    -0.06
    nika
    -0.06
    otic
    -0.06
    igration
    -0.06
    字符
    -0.06
    POSITIVE LOGITS
     intertwined
    0.07
    ';↵↵↵
    0.07
     Jeep
    0.07
          ↵↵
    0.06
            ↵    ↵
    0.06
    ?"↵↵
    0.06
    "↵↵
    0.06
        
↵
↵
    0.06
    ')):↵
    0.06
     siyaset
    0.06
    Act Density 0.020%

    No Known Activations