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

    Neuronpedia

    INDEX
    Explanations

    percentages and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raj
    -0.08
    -phone
    -0.07
    resident
    -0.06
    iming
    -0.06
    _delay
    -0.06
    辇
    -0.06
    旁
    -0.06
    Reload
    -0.06
    _stderr
    -0.06
    .redirect
    -0.06
    POSITIVE LOGITS
    万亿元
    0.08
     katılı
    0.08
    쳇
    0.07
    憷
    0.07
     Thực
    0.07
    脸部
    0.07
    컫
    0.07
    塥
    0.07
    就连
    0.06
    펄
    0.06
    Act Density 0.030%

    No Known Activations