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

    Neuronpedia

    INDEX
    Explanations

    phone call away

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    要加强
    -0.08
    /qu
    -0.07
     ====
    -0.07
    =z
    -0.07
    أهمية
    -0.07
    regular
    -0.07
    qu
    -0.07
    되기
    -0.07
     bush
    -0.07
    قيام
    -0.07
    POSITIVE LOGITS
    Lite
    0.08
    钭
    0.07
     compromised
    0.07
     свои
    0.07
     OLED
    0.07
     jersey
    0.07
    
    0.07
    ဎ
    0.07
     ViewPager
    0.06
    .owner
    0.06
    Act Density 0.019%

    No Known Activations