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

    Neuronpedia

    INDEX
    Explanations

    >true or >false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     abduction
    -0.06
     оформ
    -0.06
     UIG
    -0.06
     parç
    -0.06
    notin
    -0.06
    ,err
    -0.06
     depot
    -0.06
     dışı
    -0.06
     вост
    -0.06
     يوم
    -0.06
    POSITIVE LOGITS
    _ASCII
    0.07
    Ti
    0.07
    мін
    0.06
    еди
    0.06
    らない
    0.06
    _DET
    0.06
    glfw
    0.06
    арат
    0.06
     demasi
    0.06
    ルフ
    0.06
    Act Density 0.003%

    No Known Activations