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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    과
    -0.08
    應
    -0.07
     choked
    -0.07
    应
    -0.06
    _ing
    -0.06
     차
    -0.06
     Rangers
    -0.06
     subtitle
    -0.06
    作
    -0.06
    oliday
    -0.06
    POSITIVE LOGITS
    _HEAP
    0.07
    SOFTWARE
    0.07
     conte
    0.06
    _excel
    0.06
    /read
    0.06
    Monitoring
    0.06
     MQTT
    0.06
     untrue
    0.06
     Stadt
    0.06
     فرض
    0.06
    Act Density 0.077%

    No Known Activations