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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    语法
    -0.07
    .middleware
    -0.07
     массив
    -0.07
    低于
    -0.07
    Xd
    -0.07
     vaccinations
    -0.07
    argument
    -0.07
     oz
    -0.07
    准确性
    -0.07
     Juda
    -0.06
    POSITIVE LOGITS
    .Intent
    0.07
    aved
    0.07
    겆
    0.07
     HUGE
    0.06
    SCALL
    0.06
    荽
    0.06
    POSITORY
    0.06
     כשה
    0.06
     CG
    0.06
     archaeological
    0.06
    Act Density 0.086%

    No Known Activations