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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia discussion pages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    íg
    -0.07
    pais
    -0.07
    大型
    -0.07
     fino
    -0.07
    𝄙
    -0.07
    แบ
    -0.07
     практичес
    -0.07
     staunch
    -0.07
    _phrase
    -0.06
    jsonData
    -0.06
    POSITIVE LOGITS
     waits
    0.08
    .↵↵↵↵↵
    0.07
    dated
    0.07
    ).↵↵↵↵
    0.07
     :↵↵↵↵
    0.07
     inventor
    0.07
     historian
    0.07
    进一步
    0.06
     rat
    0.06
            
↵
↵
    0.06
    Act Density 0.010%

    No Known Activations